_ registry / mcp streamable-http · checked 13m ago

showmeonmap

https://showmeonmap.com

Registry code: 59310d36d759301b

api record

ShowMeOnMap makes cartographic, data-driven maps. It fetches live public data (USGS, NASA FIRMS, NOAA, World Bank, Eurostat, US Census, OpenStreetMap and more), styles it with a legend, and cites every source on the map.

It suits requests where the answer is data on a map: natural hazards, statistics compared across regions, infrastructure and transit networks, environmental conditions, and spatial analysis (hot spots, zonal statistics, nearest neighbour, Census enrichment). It also keeps one map across several turns, so a map can be filtered, restyled or extended.

endpoint
https://showmeonmap.com/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is showmeonmap live?
Yes — it answered the hub's last check (checked 13m ago). It answered 99% of checks over the last 30 days.
Is showmeonmap free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does showmeonmap have?
32 tools: query_features, build_map, analyze, add_layer, add_fusion_layer, select_within, focus_area, run_analysis, ….
Is showmeonmap safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
98.9%

90 days 99.3%· all time 99.3%

latency
1,785ms

last good check

priced tools
0

of 32 tools

_ answered our checks, 90 days 407 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
maps travel & places geocoding & maps
used for
  • build a map from a plain english question
  • filter or restyle map layers
  • correlate two map layers
  • export a map image
  • save a reusable map workflow
takes → gives
text, data → images, data, web pages
tools
5 reads20 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 32 tools
32 auth-required 32 of 32 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • query_features auth-required 7d ago

    Evaluate a predicate against a layer's inline features and return the matching subset. No Op is emitted and the workspace is not mutated. Handy for introspection ("how many X match Y?") before deciding whether to filter, subset, or build a new layer.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId",
    "predicate"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 1000,
      "description": "Default 100, max 1000. Response sets `truncated:true` when clipped.",
      "exclusiveMinimum": 0
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "predicate": {
      "type": "object",
      "description": "Predicate in the Mongo-shape grammar. Examples: {op:\"eq\",field:\"category\",value:\"cafe\"}, {op:\"gt\",field:\"magnitude\",value:5}, {op:\"within\",geometry:{type:\"Polygon\",coordinates:[...]}}, {op:\"and\",children:[...]}. See docs/superpowers/specs/2026-04-17-workspace-ops-log-design.md §6.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 38 lines
  • build_map changes data auth-required never probed

    Make an interactive, data-driven map from a plain-language request, built from live public data with every value cited to its source. Covers natural hazards (earthquakes, wildfires, volcanoes, tropical storms, floods), weather and air quality, statistics by country, state or region (GDP, population, health, emissions — World Bank, Eurostat, US Census), infrastructure and transit (railways, power plants, transit lines, roads), parks and terrain, and points of interest from OpenStreetMap. The query carries the place, time window and any thresholds — "earthquakes above magnitude 5 near Japan this month", "GDP per capita across Europe" — and the server applies them itself. Returns a shareable link and a map_id for follow-ups (mutate_map, filter_layer, get_state); in clients that support MCP Apps the map also renders interactively in the conversation. Analysis maps (site selection, spatial analysis) can take one to three minutes: when the build outlasts one call it returns status "building" with a resume_token, and calling build_map again with the same query and that resume_token collects the map without spending credits. A request already written as OpenStreetMap tags, a bounding box, or "everything within N m of a coordinate" maps exactly through osm_features, which takes the tags and the area as given. The Op catalog and predicate grammar that downstream tools (mutate_map, filter_layer, etc.) accept are documented in the MCP resource showmeonmap://docs/workspace-ops-spec.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Natural language: \"coffee shops in Tokyo\", \"GDP by country\", \"volcanoes in Indonesia\", etc."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "resume_token": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$",
      "description": "Only when a previous build_map returned status \"building\": its resume_token, to collect that map. Collecting spends no credits."
    }
  }
}
    arguments 24 lines
  • analyze auth-required never probed

    One call for a question that combines datasets: "which Asian capitals had the most earthquakes within 300 km this month", "people within 30 km of each volcano in Indonesia", "how much of each African country is desert". Give a plan: acquire steps (ask = a dataset in plain words answered without a model; hazard = USGS / GVP / FIRMS / GDACS; osm = exact OSM tags in an area), then op steps (within, overlap, zonal, join, population, near, rank, filter) that name their inputs by step id. The code computes, no model: returns a shareable map, a table of the answer step (top rows), a ledger naming each number's source and op, and a grounded summary. A step that cannot run fails the whole plan with that step named and why (a source that did not answer is never reported as "none"). Costs 1 credit; refunded when it fails or the answer is empty. Use build_map for a single dataset.

    mcp-tool

    {
  "type": "object",
  "required": [
    "plan"
  ],
  "properties": {
    "plan": {
      "type": "object",
      "required": [
        "steps",
        "answer"
      ],
      "properties": {
        "steps": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "n": {
                "type": "integer",
                "maximum": 100,
                "minimum": 1
              },
              "by": {
                "type": "string",
                "description": "rank: the field, e.g. \"within_count\", \"overlap_share\", \"population\""
              },
              "id": {
                "type": "string",
                "maxLength": 32,
                "minLength": 1,
                "description": "Step id (letters, digits, _); later steps name their inputs by it"
              },
              "op": {
                "enum": [
                  "within",
                  "overlap",
                  "population",
                  "near",
                  "rank",
                  "filter",
                  "zonal",
                  "join"
                ],
                "type": "string",
                "description": "within: count (and sum/max of value_field) of source points within radius_km of each target · overlap: share of each target polygon covered by source polygons · zonal: each polygon of zones gains the count (and stats of value_field) of the points inside it · join: each point of target gains the attributes of the source polygon it falls in · population: WorldPop people in each polygon or within radius_km of each point (≤ 15 features — narrow first with filter or rank) · near: nearest source to each target · rank: sort a step by a field, top n (a later step can read the top n) · filter: keep the features of input matching where"
              },
              "input": {
                "type": "string",
                "description": "population / rank: the step read"
              },
              "order": {
                "enum": [
                  "desc",
                  "asc"
                ],
                "type": "string"
              },
              "stats": {
                "type": "array",
                "items": {
                  "enum": [
                    "count",
                    "sum",
                    "mean",
                    "min",
                    "max"
                  ],
                  "type": "string"
                },
                "description": "zonal: which statistics of value_field"
              },
              "title": {
                "type": "string",
                "maxLength": 80,
                "minLength": 1,
                "description": "acquire: the layer title"
              },
              "where": {
                "type": "object",
                "description": "filter: a query_features predicate, e.g. {op:\"gte\",field:\"magnitude\",value:5}, {op:\"in\",field:\"country\",values:[\"Japan\",\"Chile\"]}, {op:\"and\",children:[…]}",
                "propertyNames": {
                  "type": "string"
                },
                "additionalProperties": {}
              },
              "zones": {
                "type": "string",
                "description": "zonal: the polygon step"
              },
              "fields": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "join: which source fields to copy (default all)"
              },
              "points": {
                "type": "string",
                "description": "zonal: the point step"
              },
              "prefix": {
                "type": "string",
                "description": "join: prefix for the copied fields"
              },
              "source": {
                "type": "string",
                "description": "within / overlap / near: the step counted or measured"
              },
              "target": {
                "type": "string",
                "description": "within / overlap / near: the step that gets the result"
              },
              "acquire": {
                "type": "object",
                "properties": {
                  "ask": {
                    "type": "string",
                    "maxLength": 300,
                    "minLength": 3,
                    "description": "A dataset in the words a single map takes, answered without a model: \"capitals of Asia\", \"volcanoes in Indonesia\", \"hospitals in Lima\", \"highest mountains in Africa\""
                  },
                  "osm": {
                    "type": "object",
                    "required": [
                      "tags"
                    ],
                    "properties": {
                      "bbox": {
                        "type": "array",
                        "items": {
                          "type": "number"
                        },
                        "maxItems": 4,
                        "minItems": 4
                      },
                      "tags": {
                        "type": "array",
                        "items": {
                          "type": "string",
                          "maxLength": 200,
                          "minLength": 3
                        },
                        "maxItems": 12,
                        "minItems": 1,
                        "description": "As osm_features: \"amenity=hospital\", \"place=town|village\", \"healthcare=*\""
                      },
                      "place": {
                        "type": "string",
                        "maxLength": 200,
                        "minLength": 2
                      },
                      "point": {
                        "type": "array",
                        "items": {
                          "type": "number"
                        },
                        "maxItems": 2,
                        "minItems": 2,
                        "description": "[lon, lat] with radius_m"
                      },
                      "radius_m": {
                        "type": "number",
                        "maximum": 50000,
                        "exclusiveMinimum": 0
                      }
                    }
                  },
                  "days": {
                    "type": "integer",
                    "maximum": 365,
                    "minimum": 1
                  },
                  "layer": {
                    "type": "string",
                    "maxLength": 200,
                    "minLength": 1,
                    "description": "With map_id: a layer already on that map, by the id get_state lists"
                  },
                  "place": {
                    "type": "string",
                    "maxLength": 120,
                    "minLength": 1,
                    "description": "hazard: country, region or continent; omit for the world"
                  },
                  "hazard": {
                    "enum": [
                      "earthquakes",
                      "volcanoes",
                      "active_fires",
                      "disasters"
                    ],
                    "type": "string",
                    "description": "earthquakes = USGS (M4.5+, past 30 days unless min_magnitude / days); volcanoes = Smithsonian GVP; active_fires = NASA FIRMS (1–10 days); disasters = GDACS"
                  },
                  "min_magnitude": {
                    "type": "number",
                    "maximum": 10,
                    "minimum": 0
                  }
                },
                "description": "Load a dataset: exactly one of ask, hazard or osm"
              },
              "radius_km": {
                "type": "number"
              },
              "sum_fields": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              },
              "value_field": {
                "type": "string"
              },
              "source_field": {
                "type": "string"
              },
              "max_distance_m": {
                "type": "number"
              }
            }
          },
          "maxItems": 6,
          "minItems": 1,
          "description": "1–6 steps, at most 3 acquires, each op after the steps it reads"
        },
        "answer": {
          "type": "string",
          "description": "The step whose rows are the table (usually the last, e.g. a rank)"
        }
      },
      "description": "Acquire datasets, then compute over them. Example: [{id:\"capitals\",acquire:{ask:\"capitals of Asia\"}},{id:\"quakes\",acquire:{hazard:\"earthquakes\",place:\"Asia\",days:30}},{id:\"x\",op:\"within\",target:\"capitals\",source:\"quakes\",radius_km:300},{id:\"top\",op:\"rank\",input:\"x\",by:\"within_count\",n:10}], answer:\"top\""
    },
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "Optional: run on this map — acquire {layer} reads its layers, and the result is added to it instead of a new map"
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 250 lines
  • add_layer changes data auth-required never probed

    Append a fully-constructed LayerPlan to an existing workspace without going through NL. Pass the same shape the workspace pipeline emits — { id, title, source, viz, geometry, ... }. Takes a structured plan; natural-language edits go through mutate_map. The full LayerPlan and Op spec are documented in the MCP resource showmeonmap://docs/workspace-ops-spec.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerPlan"
  ],
  "properties": {
    "intent": {
      "enum": [
        "primary-data",
        "context-overlay",
        "reference-boundary",
        "annotation",
        "comparison",
        "other"
      ],
      "type": "string",
      "description": "Optional. Which mental model is this add_layer operating under? \"primary-data\" = the layer the user actually asked to see; \"context-overlay\" = supporting data layered on top of a primary; \"reference-boundary\" = admin/geo boundary used as a backdrop; \"annotation\" = caller-placed callout / pin layer; \"comparison\" = a layer added to compare against another; \"other\" = none of the above."
    },
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "map_id from a prior build_map call"
    },
    "layerPlan": {
      "type": "object",
      "description": "Full LayerPlan object. Must include id, title, source, viz, geometry.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 40 lines
  • add_fusion_layer changes data auth-required never probed

    Spatially join two existing layers and add a new layer that encodes both values per region as a 3x3 bivariate choropleth. Both layers must already exist in the workspace. Auto-detects the numeric value field from each layer's viz config; pass value_field_a / value_field_b to override. Returns the new layer_id, correlation r, and matched-feature count. Required: map_id, layer_a_id, layer_b_id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layer_a_id",
    "layer_b_id"
  ],
  "properties": {
    "mode": {
      "type": "string",
      "const": "bivariate",
      "default": "bivariate"
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "layer_a_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_b_id": {
      "type": "string",
      "minLength": 1
    },
    "new_layer_id": {
      "type": "string"
    },
    "value_field_a": {
      "type": "string"
    },
    "value_field_b": {
      "type": "string"
    }
  }
}
    arguments 42 lines
  • select_within changes data auth-required 7d ago

    Create a new layer containing the source layer's features that lie within the supplied polygon. The source layer is untouched. Useful for "show me only the X inside this country/bbox/hand-drawn shape."

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "sourceLayerId",
    "newLayerId",
    "selection"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "selection": {
      "type": "object",
      "required": [
        "type",
        "coordinates"
      ],
      "properties": {
        "type": {
          "enum": [
            "Polygon",
            "MultiPolygon"
          ],
          "type": "string"
        },
        "coordinates": {
          "type": "array",
          "items": {}
        }
      },
      "description": "GeoJSON Polygon or MultiPolygon in [lng,lat] coordinate order."
    },
    "newLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "Id for the new layer. Must not already be in use in this workspace."
    },
    "inheritStyle": {
      "type": "boolean",
      "description": "Default true. false emits a new layer with minimal default styling."
    },
    "sourceLayerId": {
      "type": "string",
      "minLength": 1
    }
  }
}
    arguments 55 lines
  • focus_area changes data auth-required never probed

    Refine an existing layer to a NAMED area the server resolves from OpenStreetMap — a street corridor ("Broadway from Arbutus Street to Main Street"), a place ("Mount Pleasant"), or an intersection surroundings. Pass names only, never coordinates; unresolvable names return a clarification with real nearby candidates instead of guessed geometry. Emits ordinary undoable ops (filter / new layer + camera) and a grounded summary like "kept 37 of 150 features". Costs 1 credit when a mutation lands; clarifications are refunded.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId",
    "areaRef"
  ],
  "properties": {
    "mode": {
      "enum": [
        "filter",
        "select",
        "clip"
      ],
      "type": "string",
      "description": "filter (default): hide features outside, reversible. select: copy matches into a new layer. clip: new layer with geometry trimmed at the boundary."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "areaRef": {
      "oneOf": [
        {
          "type": "object",
          "required": [
            "kind",
            "name"
          ],
          "properties": {
            "kind": {
              "type": "string",
              "const": "place"
            },
            "name": {
              "type": "string",
              "minLength": 1
            }
          }
        },
        {
          "type": "object",
          "required": [
            "kind",
            "street"
          ],
          "properties": {
            "to": {
              "type": "string",
              "minLength": 1
            },
            "from": {
              "type": "string",
              "minLength": 1
            },
            "kind": {
              "type": "string",
              "const": "corridor"
            },
            "street": {
              "type": "string",
              "minLength": 1
            },
            "bufferMeters": {
              "type": "number",
              "maximum": 1000,
              "minimum": 30
            }
          }
        },
        {
          "type": "object",
          "required": [
            "kind",
            "street",
            "cross"
          ],
          "properties": {
            "kind": {
              "type": "string",
              "const": "aroundIntersection"
            },
            "cross": {
              "type": "string",
              "minLength": 1
            },
            "street": {
              "type": "string",
              "minLength": 1
            },
            "radiusMeters": {
              "type": "number",
              "maximum": 5000,
              "minimum": 50
            }
          }
        }
      ]
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 111 lines
  • run_analysis auth-required never probed

    Compute a spatial analysis server-side and append the finished, honestly-legended result as a new layer + camera; the result REPLACES its input layer(s) (undoable). hotspot = Getis-Ord Gi*: hot/cold significance classes (99/95/90%, Benjamini-Hochberg FDR-corrected) on a numeric field, or on hex-binned point density when valueField is omitted. zonal = aggregate points into polygon zones (an existing zone layer OR a generated h3 fishnet): count/sum/mean/min/max per zone as a quantile choropleth where zero and no-data are distinct classes. enrich = join a US Census ACS indicator (median income, home value, rent, …) onto each feature by tract/county/state containment — unmatched features stay null, never zero-filled. join = spatial join (attribute transfer): each point in layerId takes properties from the joinLayerId polygon containing it (collisions prefixed, unmatched points carry NO joined fields, zero overlap is a typed rejection). merge = append two same-geometry-class layers into one dataset with a per-row source column (schemas never null-filled; class mismatch is a typed failure). near = nearest-neighbor distance columns (great-circle meters, stated — never presented as road distance). dissolve = true polygon union per attribute group (missing values form their own group; partial sums reported). Returns a grounded memo + stats payload — every number is computed, never generated; findings keep the map. Costs 1 credit when the result lands; typed failures (unknown layer, too few features, >10,000-feature cap) are refunded.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "analysis",
    "layerId"
  ],
  "properties": {
    "k": {
      "type": "integer",
      "maximum": 24,
      "minimum": 3,
      "description": "hotspot only: nearest neighbors per feature (default 8)."
    },
    "stats": {
      "type": "array",
      "items": {
        "enum": [
          "count",
          "sum",
          "mean",
          "min",
          "max"
        ],
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "zonal only: which statistics to attach per zone (default: count, plus sum/mean/min/max when valueField is set)."
    },
    "story": {
      "type": "boolean",
      "description": "Opt-in: persist the shared map with a 2-step story rail (grounded overview + analysis memo isolating the result layer) — the /m/ link opens with it."
    },
    "zones": {
      "type": "object",
      "required": [
        "kind"
      ],
      "properties": {
        "kind": {
          "type": "string",
          "const": "h3"
        },
        "resolution": {
          "type": "integer",
          "maximum": 10,
          "minimum": 3
        }
      },
      "description": "zonal only: generate an h3 hex fishnet over the source extent instead of using a zone layer (resolution 3-10, default auto). Provide EXACTLY ONE of zoneLayerId or zones.",
      "additionalProperties": false
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80,
        "minLength": 1
      },
      "maxItems": 12,
      "minItems": 1,
      "description": "join only: which join-layer properties to transfer (default: auto-select up to 12 non-internal properties, overflow reported)."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "prefix": {
      "type": "string",
      "maxLength": 20,
      "minLength": 1,
      "description": "join only: prefix for a joined field whose name collides with an existing target property (default \"join_\")."
    },
    "layerId": {
      "type": "string",
      "minLength": 1,
      "description": "The workspace layer to analyze (geojson-backed; the point source for zonal; the point TARGET for join; the styling donor for merge)."
    },
    "analysis": {
      "enum": [
        "hotspot",
        "zonal",
        "enrich",
        "join",
        "merge",
        "near",
        "within",
        "overlap",
        "population",
        "dissolve"
      ],
      "type": "string",
      "description": "Which analysis to run. 'hotspot' = Getis-Ord Gi* with FDR-corrected significance classes. 'zonal' = aggregate a point layer into polygon zones (count/sum/mean/min/max choropleth). 'enrich' = join a US Census indicator onto each feature by containment (tract/county/state). 'join' = spatial join (attribute transfer): each POINT in layerId takes the listed properties from the polygon in joinLayerId that contains it — the aggregate direction (points INTO polygons) is 'zonal'. 'merge' = append layerId + mergeLayerId (same geometry class) into ONE dataset, each row stamped with its source layer. 'near' = each POINT in layerId gains the great-circle distance to (and identity of) its nearest feature in nearLayerId. 'within' = each POINT or POLYGON in layerId gains how many POINTS of withinLayerId lie within radiusKm (great-circle; for a polygon, inside it or within radiusKm of its edge), and with valueField their sum and maximum — e.g. earthquakes within 100 km of each capital; the result is sized by that count. 'overlap' = each POLYGON in layerId gains the area and share of overlapLayerId's POLYGONS inside it, and with sumFields their values apportioned by area (estimates: census tract population inside a fire perimeter). 'population' = each POLYGON in layerId gains the people living inside it, or each POINT the people within radiusKm (WorldPop 2020 100 m estimates; at most 15 features, 7–13 s each) — e.g. people within 30 km of each volcano. 'dissolve' = union POLYGONS sharing a dissolveField value into single features (omit the field to dissolve all into one)."
    },
    "annotate": {
      "type": "boolean",
      "description": "Opt-in: place ONE callout annotation at the headline feature (hottest cluster / top zone / highest value). Label text comes only from computed values."
    },
    "geoLevel": {
      "enum": [
        "state",
        "county",
        "tract"
      ],
      "type": "string",
      "description": "enrich only: containment geography (default tract). Tract/county fetch only the states the data touches, capped at 3 — filter first or use state for wider layers."
    },
    "radiusKm": {
      "type": "number",
      "maximum": 1000,
      "minimum": 0.01,
      "description": "within (required there): the radius in km (great-circle) to count within. population: the circle round each POINT (required for points)."
    },
    "hexMeters": {
      "type": "number",
      "maximum": 50000,
      "minimum": 100,
      "description": "hotspot density mode only: hex cell spacing in meters (default auto from the data extent)."
    },
    "indicator": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "enrich only (required there): a US Census ACS preset id (e.g. 'median_household_income', 'median_home_value', 'median_rent') or a raw ACS variable code (e.g. 'B19013_001E')."
    },
    "nearField": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "near only: property of the nearest feature to copy as its identity (default: first name-like property)."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "sumFields": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80,
        "minLength": 1
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "dissolve: numeric properties to SUM per group — skipped values reported, a group with none present carries NO sum. overlap: numeric properties of overlapLayerId to apportion by area into each target."
    },
    "valueField": {
      "type": "string",
      "minLength": 1,
      "description": "Numeric property to analyze. hotspot: omit on point layers for incident-DENSITY mode (hex-binned counts). zonal: omit for count-only aggregation. within: a property of the withinLayerId points to sum and take the maximum of (e.g. mag)."
    },
    "joinLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "join only (required there): the POLYGON layer providing the attributes."
    },
    "nearLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "near only (required there): the POINT layer to search for each target point's nearest neighbor."
    },
    "sourceField": {
      "type": "string",
      "maxLength": 40,
      "minLength": 1,
      "description": "merge only: name of the per-row provenance column naming each row's source layer (default \"merge_source\"; renamed on collision, reported)."
    },
    "zoneLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "zonal only: an existing polygon layer to aggregate into. Provide EXACTLY ONE of zoneLayerId or zones."
    },
    "maxDistanceM": {
      "type": "number",
      "maximum": 20000000,
      "minimum": 1,
      "description": "near only: search radius in meters — a point whose nearest neighbor is farther carries NO near fields (reported)."
    },
    "mergeLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "merge only (required there): the second layer — same geometry class (point/line/polygon) as layerId."
    },
    "dissolveField": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "dissolve only: group-by property (omit = dissolve ALL into one footprint); missing values form their own \"(no value)\" group."
    },
    "withinLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "within only (required there): the POINT layer to count around each target point."
    },
    "overlapLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "overlap only (required there): the POLYGON layer whose area inside each target is measured."
    }
  }
}
    arguments 204 lines
  • remove_layer changes data auth-required never probed

    Drop a layer from the workspace by id. Strict: removing an already-removed or never-added layer fails. Layer ids do NOT recycle — a removed id cannot be re-added later in the same workspace. GATED: this tool is destructive. Pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "confirmed": {
      "type": "boolean",
      "description": "Set to true to confirm this destructive action. If omitted or false, the call returns a needs_confirmation envelope. Layer ids are tombstoned — once removed, the same id cannot be re-added later in this workspace."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 27 lines
  • clear_filters changes data auth-required never probed

    Wipe every predicate currently applied to a layer's filter chain, making every source feature visible again. Inverse of filter_layer. No-op on layers that have no existing filter. GATED: pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "confirmed": {
      "type": "boolean",
      "description": "Set to true to confirm this sensitive action. If omitted or false, the call returns a needs_confirmation envelope. A cleared filter chain can be restored with undo."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 27 lines
  • restyle_layer changes data auth-required never probed

    Adjust a layer's color and/or opacity. Within-palette changes only — the renderer silently ignores fields the current viz variant doesn't support. Pass at least one of color / opacity; passing neither is an accepted no-op.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId"
  ],
  "properties": {
    "color": {
      "type": "string",
      "minLength": 1,
      "description": "CSS color string: hex (#RRGGBB), rgb/rgba, or named color."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "opacity": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "0 (transparent) to 1 (opaque)."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 34 lines
  • set_camera changes data auth-required never probed

    Override the workspace camera. Latest set_camera op wins during replay. Two modes: `fitBounds` with a [w,s,e,n] bbox (plus optional padding/animateMs), or `flyTo` with [lng,lat] center + zoom (plus optional pitch/bearing/animateMs). Covers requests like "zoom to Japan", "center on Paris at z=10", or framing a filtered layer. Equivalent to the camera move mutate_map would emit, but skips the NL roundtrip.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "camera"
  ],
  "properties": {
    "camera": {
      "oneOf": [
        {
          "type": "object",
          "required": [
            "mode",
            "bounds"
          ],
          "properties": {
            "mode": {
              "type": "string",
              "const": "fitBounds"
            },
            "bounds": {
              "type": "array",
              "items": {
                "type": "number"
              },
              "maxItems": 4,
              "minItems": 4,
              "description": "[west, south, east, north] bbox in WGS84 degrees."
            },
            "padding": {
              "type": "number",
              "minimum": 0,
              "description": "Pixel padding around the bbox. Default is the renderer default."
            },
            "animateMs": {
              "type": "number",
              "minimum": 0,
              "description": "Animation duration in ms. 0 = instant jump."
            }
          }
        },
        {
          "type": "object",
          "required": [
            "mode",
            "center",
            "zoom"
          ],
          "properties": {
            "mode": {
              "type": "string",
              "const": "flyTo"
            },
            "zoom": {
              "type": "number"
            },
            "pitch": {
              "type": "number",
              "description": "Tilt in degrees, 0-60."
            },
            "center": {
              "type": "array",
              "items": {
                "type": "number"
              },
              "maxItems": 2,
              "minItems": 2,
              "description": "[lng, lat] in WGS84."
            },
            "bearing": {
              "type": "number",
              "description": "Rotation in degrees, 0-360."
            },
            "animateMs": {
              "type": "number",
              "minimum": 0,
              "description": "Animation duration in ms. 0 = instant jump."
            }
          }
        }
      ]
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 94 lines
  • set_time changes data auth-required never probed

    Override the current time-range filter. Latest set_time op wins during replay. Covers requests like "filter to 2020-2024" or "show only the last 7 days". Not yet consumed by the renderer — the UI drives the slider directly — but the value is captured in the ops log and queryable via get_state.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "field",
    "rangeStart",
    "rangeEnd"
  ],
  "properties": {
    "field": {
      "type": "string",
      "minLength": 1,
      "description": "Feature property carrying the time value (e.g. \"date\", \"year\", \"timestamp\")."
    },
    "format": {
      "enum": [
        "unix_ms",
        "iso",
        "integer"
      ],
      "type": "string",
      "description": "How rangeStart/rangeEnd encode time. Default: unix_ms at render time."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rangeEnd": {
      "type": "number",
      "description": "Inclusive upper bound of the visible window."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "rangeStart": {
      "type": "number",
      "description": "Inclusive lower bound of the visible window."
    }
  }
}
    arguments 43 lines
  • remove_annotation changes data auth-required never probed

    Drop a previously-placed annotation by id. Strict: removing an already-removed or never-placed id fails. After removal, the id CAN be re-used by a later add_annotation (unlike layer ids, which are tombstoned for the session).

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "annotationId"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "annotationId": {
      "type": "string",
      "minLength": 1
    }
  }
}
    arguments 23 lines
  • export_workspace reads auth-required never probed

    Return the current workspace document (ops log + cursor + meta) plus the materialized mapPlan and layerFilters, in a shape suitable for save-to-file / share-by-URL / inspection. Pure read — no mutation, no credit charge. This is the full raw state for serialization; get_state returns a compact summary for display.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 18 lines
  • export_layer_data auth-required never probed

    Export a single layer's features as a downloadable file. Returns a URL with Content-Disposition: attachment so the user's browser downloads it. CSV drops geometry beyond a (lng, lat) centroid — for full polygon/line geometry, use format: "geojson". The URL is an unguessable capability link that does NOT expire: anyone with the link can download the file. Required: map_id, layer_id, format.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layer_id",
    "format"
  ],
  "properties": {
    "format": {
      "enum": [
        "csv",
        "geojson"
      ],
      "type": "string"
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 31 lines
  • export_image reads auth-required never probed

    Returns a deep-link URL that opens the map in the user's browser and automatically triggers a PNG download. The user clicks the link, the browser renders the map at full resolution with the legend composited (if legend: true), and the file downloads. There is no server-side rendering; the user's browser is the renderer. Required: map_id. Optional: format (png default), legend (true default).

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "format": {
      "enum": [
        "png",
        "jpeg",
        "pdf"
      ],
      "type": "string",
      "default": "png"
    },
    "legend": {
      "type": "boolean",
      "default": true
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 31 lines
  • redo changes data auth-required never probed

    Advance the workspace cursor by one toward the tail of the ops log, replaying the next op that was previously undone. Calling redo when the cursor is already at the tail (no undone ops to fast-forward) fails rather than silently no-op. Note: any new op applied via apply-op / mutate-map after an undo truncates the redo tail (standard edit-stack semantics).

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 18 lines
  • save_workflow changes data auth-required never probed

    Save a re-runnable, parameterized workflow: an ordered list of natural-language instructions (step 1 builds, later steps mutate). Wrap values in {braces} and declare them in params. Running it later re-executes the instructions on FRESH data and bills per step like typing.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name",
    "steps"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "Workflow name."
    },
    "steps": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "instruction"
        ],
        "properties": {
          "instruction": {
            "type": "string",
            "maxLength": 4000,
            "minLength": 1
          }
        }
      },
      "maxItems": 12,
      "minItems": 1,
      "description": "Ordered NL instructions. Step 1 builds the map; later steps mutate it. Wrap values in {braces} to declare parameters."
    },
    "params": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "label",
          "kind"
        ],
        "properties": {
          "kind": {
            "enum": [
              "place",
              "number",
              "text",
              "timerange"
            ],
            "type": "string"
          },
          "name": {
            "type": "string",
            "maxLength": 40,
            "minLength": 1
          },
          "label": {
            "type": "string",
            "maxLength": 80,
            "minLength": 1
          },
          "default": {
            "type": "string",
            "maxLength": 200
          }
        }
      },
      "maxItems": 8,
      "description": "Declared parameters — every {slot} used in steps must be declared here."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 78 lines
  • osm_features auth-required never probed

    Map and list OpenStreetMap objects matching exact OSM tags inside an area — a bbox, a point and radius, or a named place. Use when you know the tags ("place=village|hamlet", "amenity=clinic", "railway=tram", "highway=*+name=Rue de Lyon") or need everything near a coordinate with distances; use build_map for natural-language questions and statistics. No model interpretation: tags and area are taken as given, every feature is an OSM object with all its tags. Each layer reports ok / empty (OSM has none matching here) / unavailable (no source answered — says nothing about whether any exist). Returns a shareable map plus a compact table per layer (name, osm id, distance_m for point searches, address, coordinates). Costs 1 credit; refunded when no layer has a feature.

    mcp-tool

    {
  "type": "object",
  "required": [
    "layers",
    "area"
  ],
  "properties": {
    "area": {
      "type": "object",
      "properties": {
        "bbox": {
          "type": "array",
          "items": {
            "type": "number"
          },
          "maxItems": 4,
          "minItems": 4,
          "description": "[west, south, east, north] in degrees"
        },
        "place": {
          "type": "string",
          "maxLength": 200,
          "minLength": 2,
          "description": "A named place whose extent is the area, e.g. \"Lahore, Pakistan\""
        },
        "point": {
          "type": "object",
          "required": [
            "lat",
            "lon"
          ],
          "properties": {
            "lat": {
              "type": "number",
              "maximum": 90,
              "minimum": -90
            },
            "lon": {
              "type": "number",
              "maximum": 180,
              "minimum": -180
            }
          }
        },
        "radius_m": {
          "type": "number",
          "maximum": 50000,
          "description": "With point, or with place (a radius around that place): search radius in metres; results carry distance_m",
          "exclusiveMinimum": 0
        }
      },
      "description": "Exactly one of: bbox, point + radius_m, or place (its extent; add radius_m for a radius around it, e.g. an address). Areas up to ~300 km across."
    },
    "limit": {
      "type": "integer",
      "maximum": 1000,
      "description": "Max features per layer (default 200)",
      "exclusiveMinimum": 0
    },
    "layers": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "tags"
        ],
        "properties": {
          "tags": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 200,
              "minLength": 3
            },
            "maxItems": 12,
            "minItems": 1,
            "description": "OSM tags, any of which matches: \"amenity=clinic\", \"place=village|town\" (any of the values), \"healthcare=*\" (key present), \"railway=construction+construction=tram\" (+ = AND)"
          },
          "title": {
            "type": "string",
            "maxLength": 80,
            "minLength": 1,
            "description": "Legend title for this layer, e.g. \"Health facilities\""
          }
        }
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "1–5 layers, each drawn and listed separately"
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 99 lines
  • rename_layer changes data auth-required never probed

    Change a layer's id from oldLayerId to newLayerId. Re-keys any existing filter chain and preserves insertion order among sibling layers. Strict: newLayerId must not already be in use (current OR tombstoned) in this workspace. Subsequent ops must reference the layer by its new id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "oldLayerId",
    "newLayerId"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "newLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "New id. Must be unique within the workspace."
    },
    "oldLayerId": {
      "type": "string",
      "minLength": 1
    }
  }
}
    arguments 29 lines
  • tag changes data auth-required never probed

    Label the current workspace state with a user-supplied name. The label is mirrored into workspace.meta.tags so UIs can render a named-revision history. Tagging the same label twice is idempotent — no error, no duplicate entry.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Checkpoint label, e.g. \"before EV layer added\" or \"v1.0\"."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 24 lines
  • run_workflow changes data auth-required never probed

    Execute a saved workflow with parameter values. PAID: bills ~1 credit per step through the normal build/mutate paths (the estimate is in list_workflows). Optional batch mode sweeps ONE param across 2–20 values — each value is a full independent run (steps × values credits); failed/paused values are reported per value and the batch continues. A clarification pauses a single run (status "paused" + the question); failures stop at the failing step. On success the result is a live map with a shareable URL (batch: the last successful value's map).

    mcp-tool

    {
  "type": "object",
  "required": [
    "workflow_id"
  ],
  "properties": {
    "batch": {
      "type": "object",
      "required": [
        "param",
        "values"
      ],
      "properties": {
        "param": {
          "type": "string",
          "minLength": 1,
          "description": "The ONE declared param to sweep (must not also be in params)."
        },
        "values": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "maxItems": 20,
          "minItems": 2,
          "description": "2–20 values; each is a FULL independent billed run."
        }
      },
      "description": "Batch mode: run the workflow once per value (\"each of the 12 districts\"). Bills steps × values."
    },
    "params": {
      "type": "object",
      "description": "Values for the workflow's declared parameters.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": "string"
      }
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "workflow_id": {
      "type": "string",
      "minLength": 1,
      "description": "From save_workflow or list_workflows."
    }
  }
}
    arguments 54 lines
  • get_state reads auth-required 7d ago

    Return the current workspace, map plan, and active filters for a given map_id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 18 lines
  • mutate_map changes data auth-required never probed

    Apply a natural-language instruction to an existing workspace. Valid mutations: filter a layer, remove a layer, change camera, change basemap. For ambiguous instructions the tool emits a clarification field. For unrelated instructions it emits outOfScope — build a new map in that case. The full Op catalog and predicate grammar are documented in the MCP resource showmeonmap://docs/workspace-ops-spec.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "instruction"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "map_id from a prior build_map call"
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "instruction": {
      "type": "string",
      "minLength": 1,
      "description": "e.g., \"filter to where magnitude is greater than 5\", \"change basemap to dark\""
    }
  }
}
    arguments 25 lines
  • correlate_layers reads auth-required 8d ago

    Spatially join two existing workspace layers and return the Pearson correlation coefficient r, sample size n, two-sided p-value approximation, plus human-readable strength and direction labels. Pure read — no layer is added, no op is committed, no credit charge. Returns numbers only; add_fusion_layer renders the same join as a map layer. Required: map_id, layer_a_id, layer_b_id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layer_a_id",
    "layer_b_id"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "layer_a_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_b_id": {
      "type": "string",
      "minLength": 1
    },
    "value_field_a": {
      "type": "string"
    },
    "value_field_b": {
      "type": "string"
    }
  }
}
    arguments 34 lines
  • add_annotation changes data auth-required never probed

    Add a user-placed label at a specific coordinate. Annotations are independent of layers and live in their own id namespace. Strict: the id must not already be in use by another CURRENTLY-placed annotation (removed ids can be recycled).

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "id",
    "coords"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "Stable id for this annotation — caller-supplied."
    },
    "color": {
      "type": "string",
      "minLength": 1,
      "description": "Optional CSS color for the marker + label."
    },
    "label": {
      "type": "string",
      "description": "Optional text rendered at the point."
    },
    "coords": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "maxItems": 2,
      "minItems": 2,
      "description": "[lng, lat] in WGS84."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 43 lines
  • undo auth-required never probed

    Rewind the workspace cursor by one, re-materializing the state as it was before the last mutation. Does NOT delete any ops — redo will fast-forward. Calling undo at the workspace genesis (cursor === 0, only the CreateWorkspace op is in scope) is a no-op that surfaces an error rather than silently doing nothing. GATED: pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "confirmed": {
      "type": "boolean",
      "description": "Set to true to confirm this sensitive action. If omitted or false, the call returns a needs_confirmation envelope. Undo rewinds the most recent change; redo restores it."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 22 lines
  • report_blocker changes data auth-required never probed

    Send the ShowMeOnMap team a report about a request this server could not complete — an unsupported intent, a missing tool, an unclear schema, or an op that failed in a confusing way. Records the report to a server-side log for future capability work; it does not change the current map or session. map_id is optional, so a report can be filed before any map exists.

    mcp-tool

    {
  "type": "object",
  "required": [
    "what_i_was_trying",
    "what_i_tried",
    "where_i_got_stuck"
  ],
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "Optional. The map_id you were working on, if any."
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    },
    "what_i_tried": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "Which tools / inputs you attempted, in order. Be specific — tool name + key arg shape is ideal."
    },
    "what_i_was_trying": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "High-level intent in one or two sentences. e.g. \"merge two filtered choropleths into a fused bivariate map\"."
    },
    "where_i_got_stuck": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "The specific failure: what came back, what was missing, why you could not proceed."
    },
    "suggested_capability": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional. A new tool, op, or schema field that would have unblocked you."
    }
  }
}
    arguments 45 lines
  • list_workflows reads auth-required 6d ago

    List the caller's saved workflows with their parameters and per-run credit estimates.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 11 lines
  • get_map_view auth-required 8d ago

    Used by the ShowMeOnMap map card to load a map version. Not for the model.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id"
  ],
  "properties": {
    "op_id": {
      "type": "string",
      "minLength": 1
    },
    "cursor": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": 0
    },
    "map_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{1,128}$"
    },
    "layer_ids": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 50
    }
  }
}
    arguments 29 lines
  • filter_layer changes data auth-required never probed

    Narrow a layer to features matching a structured predicate. `append:true` (default) conjoins with any existing filter; `append:false` replaces the chain.

    mcp-tool

    {
  "type": "object",
  "required": [
    "map_id",
    "layerId",
    "predicate"
  ],
  "properties": {
    "append": {
      "type": "boolean",
      "description": "Default true. false replaces the layer's existing filter chain."
    },
    "intent": {
      "enum": [
        "narrow",
        "isolate-outliers",
        "compare-subset",
        "preview-data",
        "other"
      ],
      "type": "string",
      "description": "Optional. Which mental model is this filter operating under? \"narrow\" = generic shrink-the-set; \"isolate-outliers\" = pull out anomalies for inspection; \"compare-subset\" = pre-step before a side-by-side compare; \"preview-data\" = exploratory peek; \"other\" = none of the above."
    },
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1,
      "description": "id of the layer to filter"
    },
    "predicate": {
      "type": "object",
      "description": "Predicate in the Mongo-shape grammar. Examples: {op:\"eq\",field:\"category\",value:\"cafe\"}, {op:\"gt\",field:\"magnitude\",value:5}, {op:\"within\",geometry:{type:\"Polygon\",coordinates:[...]}}, {op:\"and\",children:[...]}. See docs/superpowers/specs/2026-04-17-workspace-ops-log-design.md §6.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "rationale": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Optional short label (≤300 chars) for the map edit history, e.g. \"add wildfire layer\". Omit it to send nothing beyond the tool arguments."
    }
  }
}
    arguments 48 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 59310d36d759301b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/59310d36d759301b/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/59310d36d759301b/badge.svg)](https://brick.blue/agent/59310d36d759301b?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.