_ registry / mcp + a2a http-sse · checked 2h ago

astranl-mcp

https://astranl.com

Registry code: 691bf56bc330a5db

api record

AstraNL connects a real task to a verified real-world outcome in the Netherlands and returns evidence another system can check. If you do not know which tool fits, call ask_astranl with your task in plain words: it returns which tool to call, what to supply, what can and cannot be verified, and whether AstraNL can help at all. To have a task executed use create_task; to follow it use check_task; for signed evidence use get_evidence; to check a reference someone gave you use verify_astranl; for source-linked context on tenders or products use ground_astranl. To know whether a machine, robot or…

endpoint
https://astranl.com/mcp/streamable
door code
c86e810a5646a567
protocol
http-sse ·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 astranl-mcp live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is astranl-mcp free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does astranl-mcp have?
31 tools: fetch, nl_municipal_build_rules, get_evidence, search, check_counterparty_nl, check_task, estimate_cost, ground_component, ….
Is astranl-mcp 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
99.6%

90 days 99%· all time 99.8%

latency
88ms

last good check

priced tools
0

of 31 tools

_ answered our checks, 90 days 969 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
productivity & business
used for
  • route a real-world task in the netherlands
  • check a dutch counterparty
  • coordinate a verified executor
  • verify task evidence
takes → gives
text → data
tools
8 reads2 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 31 tools
9 open2 auth-required 20 never probed 11 of 31 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.

  • construction_events open 2h ago

    CloudEvents 1.0 feed of construction signals, oldest first after since_id: daily permit aggregate cells (with gate B accuracy), newly published works tenders (AAO), laws coming up. Continue with next_since_id. Permit aggregates only: no permit rows, publication identifiers, titles, addresses, points or names; permit counts below 5 per authority per kind are shown as <5 and totals that would reveal one are lower bounds (>=n). Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "type": {
      "enum": [
        "nl.astranl.construction.permits.daily",
        "nl.astranl.construction.tender.published",
        "nl.astranl.construction.law.upcoming"
      ],
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "events per page, default 25"
    },
    "since_id": {
      "type": "string",
      "maxLength": 40,
      "description": "sequence number or event id cs-... to continue after"
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • construction_permits open 16h ago

    Official permit publications counted per issuing body (municipality, province, water board) and kind (application, granted, refused, ...) over the last N days (default 90, max 400). Permit kind accuracy is measured, not assumed: manual validation gate B on a 200-row sample (2026-10-05) gave precision 0.98, Wilson 95% lower bound 0.94, 11% unclassified; the current figures come back in accuracy, and the unknown bucket (OVERIG, BESLUIT_ONBEKEND) is shown separately. Permit aggregates only: no permit rows, publication identifiers, titles, addresses, points or names; permit counts below 5 per authority per kind are shown as <5 and totals that would reveal one are lower bounds (>=n). Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 400,
      "minimum": 1,
      "description": "window in days, default 90"
    },
    "gemeente": {
      "type": "string",
      "maxLength": 80,
      "description": "municipality / issuing body as published, e.g. Utrecht"
    },
    "max_municipalities": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "cap the municipality list for context size, default 40"
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • construction_summary open 16h ago

    One-call overview of Dutch construction facts: permit publications last 90 days (national), lead-time status, number of open public works tenders, latest CBS periods, construction laws taking effect in the next 365 days. Permit kind accuracy is measured, not assumed: manual validation gate B on a 200-row sample (2026-10-05) gave precision 0.98, Wilson 95% lower bound 0.94, 11% unclassified; the current figures come back in accuracy, and the unknown bucket (OVERIG, BESLUIT_ONBEKEND) is shown separately. Permit aggregates only: no permit rows, publication identifiers, titles, addresses, points or names; permit counts below 5 per authority per kind are shown as <5 and totals that would reveal one are lower bounds (>=n). Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • construction_leadtimes open 2h ago

    Permit lead times (application to decision, median and quartiles) from official pairs. Currently CLOSED: the answer says CLOSED with the reason until validation gate C passes; no lead time is estimated before that. Permit aggregates only: no permit rows, publication identifiers, titles, addresses, points or names; permit counts below 5 per authority per kind are shown as <5 and totals that would reveal one are lower bounds (>=n). Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "gemeente": {
      "type": "string",
      "maxLength": 80,
      "description": "municipality / issuing body as published, e.g. Utrecht"
    }
  },
  "additionalProperties": false
}
    arguments 11 lines
  • construction_laws open 2h ago

    Construction law calendar: dated rules in force or planned (Omgevingswet, Wkb, EPBD IV, MPG, CPR, ...), each with its own official or sector source and last-verified date; rows whose planned date passed are flagged needs_reverify. Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "upcoming_days": {
      "type": "integer",
      "maximum": 3650,
      "minimum": 0,
      "description": "only rules taking effect within this many days"
    }
  },
  "additionalProperties": false
}
    arguments 12 lines
  • construction_economy open 10h ago

    CBS construction economy: build cost input price index, construction bankruptcies, construction vacancy rate (latest stored period, CBS status Voorlopig/Definitief per row, freshness) plus CBS indicators (dwelling permits, establishments, labour). Provisional figures are revised by CBS. Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • construction_natura open 16h ago

    Natura 2000 sites in the Netherlands from RVO / PDOK: number, site label, protection type, status, site code, bounding box (lon/lat). Filter with site. Source recount is reported. Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "site": {
      "type": "string",
      "maxLength": 80,
      "description": "case-insensitive filter on the site label"
    }
  },
  "additionalProperties": false
}
    arguments 11 lines
  • construction_tenders open 13h ago

    Open Dutch public works tenders from TenderNed (announcements with a future closing date): buyer, CPV, procedure, published and closing date, days left, European flag, TenderNed id and link. Tender names are not returned; open the link for the full notice. Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • construction_zones open 13h ago

    Dutch zero-emission and low-emission zones from NDW as published: municipality, zone label, status, start, vehicle categories, transition rules, bbox centre; derived_ze_logistics is derived by AstraNL. Source recount (ids and hashes) is reported. Read-only. Every answer carries source provenance (source, source_url, licence, as_of, retrieved_at = when AstraNL last read the source, served_at, method, status) and an exposure block.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "gemeente": {
      "type": "string",
      "maxLength": 80,
      "description": "municipality / issuing body as published, e.g. Utrecht"
    }
  },
  "additionalProperties": false
}
    arguments 11 lines
  • check_estimate_materials auth-required 18h ago

    Check every material line of an AstraNL estimate case you hold the token of (from estimate_case_create) against the current offer of the same product: PRICE_UP or PRICE_DOWN beyond 5 percent, UNAVAILABLE, NOT_FOUND_IN_CHECKED_SOURCES, CHEAPER_SAME_GTIN at another store, each with source and read time, plus the open findings of the daily monitor for that case. Read-only; an estimate is re-read live at most once in 6 hours.

    mcp-tool

    {
  "type": "object",
  "required": [
    "case_id",
    "token"
  ],
  "properties": {
    "token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 256,
      "minLength": 1
    },
    "case_id": {
      "type": "string",
      "pattern": "^ESTREQ-[0-9]{8}-[0-9a-f]{8}$"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • estimate_case_status auth-required 21h ago

    Read the exact public case-status JSON using case_id and its token. Human-client questions and documents retain their language. Deliver an estimate only when release_state is RELEASED; DONE alone is insufficient.

    mcp-tool

    {
  "type": "object",
  "required": [
    "case_id",
    "token"
  ],
  "properties": {
    "token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 256,
      "minLength": 1
    },
    "case_id": {
      "type": "string",
      "pattern": "^ESTREQ-[0-9]{8}-[0-9a-f]{8}$"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • fetch reads unknown 8h ago

    Fetch the full record for a single result id returned by search (robot passport, category detail, or merchant SKU). Read-only.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 120,
      "description": "Result id from search (e.g. robot:DJI-Matrice, sku:16759:Green-flor)."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • nl_municipal_build_rules unknown 8h ago

    Dutch municipal rules for a renovation or building job, with ONE read-only call. Give a municipality, optionally the planned bouwkosten excluding VAT. Returns the 2026 omgevingsvergunning fee, leges, for the technical building activity as the municipality's own regulation sets it, and whether a skip or container on the public road needs a permit, a notification or nothing, with the permit fee and precario where confirmed. Every answer names the regulation, article and source URL, the read date and how it was verified. Coverage: all 342 municipalities for leges, 296 for containers. Limits: the municipality decides; spatial or other permit parts are not added; a fee is withheld when the tariff is not verified. Free, no auth, no side effects.

    mcp-tool

    {
  "type": "object",
  "required": [
    "municipality"
  ],
  "properties": {
    "municipality": {
      "type": "string",
      "maxLength": 80,
      "minLength": 2,
      "description": "Dutch municipality name or CBS code, e.g. Zaanstad or GM0479"
    },
    "bouwkosten_eur": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 0,
      "description": "planned construction cost excluding VAT in euro; default 50000"
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • get_evidence reads unknown 24h ago

    Machine-checkable evidence for an AstraNL task, action or receipt: the signed log events that mention it, each verified live, with a proof block stating what is verified, what is not, validity, status, limitations and next actions.

    mcp-tool

    {
  "type": "object",
  "required": [
    "task_id"
  ],
  "properties": {
    "task_id": {
      "type": "string",
      "maxLength": 40,
      "description": "task id, action id or receipt id"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • search reads unknown 18h ago

    Search AstraNL coordination data (robots registry, service categories, and merchant parts by keyword). Returns a list of results, each with an id and a short title/snippet, for use with the fetch tool. Read-only. This is the generic discovery entry point expected by agent frameworks.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 120,
      "description": "Free-text search query."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • check_counterparty_nl reads unknown 10h ago

    Check a Dutch or EU counterparty against official sources before your own next step, such as onboarding a supplier, paying an invoice or signing an order. Give the KvK number, the company name and the EU VAT number as your document states them. Returns verdicts, not register data: whether the KvK number has an active registration, whether the name matches a registered name, whether the VAT number is valid in VIES and whether its VIES name matches the register, EU sanctions list candidates, whether an insolvency case is published under the KvK number in the Dutch insolvency register, open questions and a check_id. Read-only, no key, no cost. AstraNL does not search the Dutch register by name; look a number up at kvk.nl. When a colleague or auditor must verify it later, call record_counterparty_check with the check_id. It does not prove who may sign for the company, who owns a bank account, solvency or reliability.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "city": {
      "type": "string",
      "maxLength": 80,
      "description": "not used; kept for compatibility, AstraNL does not search the register by name"
    },
    "purpose": {
      "type": "string",
      "maxLength": 200,
      "description": "optional: the next action you are about to take, for example approve supplier or pay invoice"
    },
    "kvk_number": {
      "type": "string",
      "maxLength": 12,
      "description": "Dutch KvK number, 8 digits, as printed on the invoice, quote or website"
    },
    "vat_number": {
      "type": "string",
      "maxLength": 20,
      "description": "EU VAT number with country prefix, for example NL810433941B01"
    },
    "company_name": {
      "type": "string",
      "maxLength": 200,
      "description": "the company name exactly as your document or contact states it"
    }
  },
  "minProperties": 1,
  "additionalProperties": false
}
    arguments 32 lines
  • check_task reads unknown 10h ago

    Current state of a task or ingress receipt from create_task, and who must act next. Returns only what is recorded; infers nothing.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string",
      "maxLength": 40,
      "description": "task id from check_task or a case"
    },
    "receipt_id": {
      "type": "string",
      "maxLength": 40,
      "description": "RCPT-n from create_task"
    },
    "receipt_key": {
      "type": "string",
      "maxLength": 80,
      "description": "owner key shown once by create_task; without it links are read-only"
    }
  },
  "minProperties": 1,
  "additionalProperties": false
}
    arguments 22 lines
  • estimate_cost unknown 21h ago

    Instant planning cost figure in EUR for one job category in the Netherlands (not a quote; answers in under 2 s). labor_cost = labor_hours x labor_rate x location_mult, always. The rate comes from AstraNL's S_PRICEBASE (CAO wage with employer cost, overhead and profit) or its labour cost canon; hours from CBS-derived norms where AstraNL has one, otherwise a planning factor labelled ASSUMPTION; location_mult is 1.0 with its basis (no sourced regional factor for renovation labour). Each material line says price_source live_read (store, read_at, product link) or indicative (basis and date). No robot price or savings is given without evidence. Sources are in estimate.labour and estimate.materials. For a reviewed estimate of a real job use estimate_case_create, then estimate_case_status and estimate_case_answer; estimate_case_files for photos or plans and estimate_case_video for video intake. Read-only, free.

    mcp-tool

    {
  "type": "object",
  "required": [
    "category"
  ],
  "properties": {
    "area_m2": {
      "type": "number",
      "maximum": 100000,
      "minimum": 0,
      "description": "Surface area or working volume in square meters. Optional but improves accuracy. For non-area tasks (e.g. plumbing repair) pass 0 or omit."
    },
    "category": {
      "enum": [
        "painting",
        "cleaning",
        "plumbing",
        "roofing",
        "renovation",
        "electrical",
        "garden",
        "repair",
        "moving",
        "construction",
        "delivery",
        "logistics",
        "energy",
        "solar",
        "hvac",
        "automotive",
        "welding",
        "manufacturing",
        "installation",
        "maintenance",
        "inspection",
        "carpentry",
        "flooring",
        "demolition",
        "insulation",
        "glazing"
      ],
      "type": "string",
      "description": "Service category. Same enum as create_task."
    },
    "location": {
      "type": "string",
      "maxLength": 80,
      "description": "City in the Netherlands. Pricing varies by region (Amsterdam tends to be highest). Optional — omitting uses national median."
    }
  },
  "additionalProperties": false
}
    arguments 52 lines
  • ground_component unknown 9d ago

    Ground a machine, robot or industrial automation component in live market reality with ONE call. Give a manufacturer part number and optionally the maker. AstraNL queries its verified distributor connections (Nexar/Octopart, Mouser, element14/Farnell NL, OEMsecrets) in parallel, keeps only offers whose part number matches exactly after normalisation, screens maker and sellers against the EU consolidated sanctions list and the US Consolidated Screening List, and returns availability, stock seen, authorized sellers, lowest unit price seen in EUR, lifecycle values and per-source status. When AstraNL holds the manufacturer own lifecycle or discontinuation page for the part, the answer also carries manufacturer_lifecycle: status, date, the successor the manufacturer names and the page SHA-256, kept separate from seller-reported values; asking for a successor also shows which discontinued part it replaces. Every fresh answer carries a SHA-256 digest sealed with the AstraNL moment seal and an AstraLock event id you can check later with verify_astranl. Limits: distributor data is seller-reported at the observed time, not a quote and not a delivery promise; NOT_FOUND_IN_CHECKED_SOURCES means only these sources; answers are cached for 24 hours. Never orders, contacts or pays anyone. Writes (why the tool is not read-only): each fresh answer, not one served from the 24 hour cache, appends one event to the public AstraLock log with the part number, the maker, the digest, the availability and the number of exact offers, so the answer can be verified later, and stores the answer in an AstraNL database table (component_groundings) that serves the cache and counts the budget; the row names only the door (mcp), nothing about the caller. Live budget: 40 fresh reads a day across all MCP callers; after that only cached answers, status DAILY_LIVE_BUDGET_SPENT. Logging: every MCP call is journaled with the tool name, outcome, argument length, caller class (external, probe, crawler, self), a SHA-256 hash of the caller network /24 and the client family; for demand statistics also the first 160 characters of a query, question, title or id argument and the user-agent; never the address itself, other arguments or an account.

    mcp-tool

    {
  "type": "object",
  "required": [
    "mpn"
  ],
  "properties": {
    "mpn": {
      "type": "string",
      "maxLength": 80,
      "minLength": 3,
      "description": "manufacturer part number, exactly as printed by the maker, e.g. 1756-L85E"
    },
    "manufacturer": {
      "type": "string",
      "maxLength": 80,
      "description": "optional maker name, e.g. Allen-Bradley; offers from other makers are then dropped"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • ask_astranl reads unknown 8h ago

    Turn a real-world task or question into a routing decision: whether AstraNL can help, which one tool to call, what to supply, what can and cannot be verified. No commitment, nothing created, no key. Also answers whether a physical task is feasible in the Netherlands.

    mcp-tool

    {
  "type": "object",
  "required": [
    "question"
  ],
  "properties": {
    "question": {
      "type": "string",
      "maxLength": 400,
      "description": "your task or question in plain words, any language"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • create_task changes data unknown never probed

    Ask AstraNL to find and coordinate a verified executor for a physical task in the Netherlands. Returns an ingress receipt at once and a case once planning found a path; the client pays the executor directly; AstraNL holds no money. Fee: submitting costs nothing; AstraNL charges 1 percent of the transaction only when it coordinated a completed paid task, nothing else.

    mcp-tool

    {
  "type": "object",
  "required": [
    "need"
  ],
  "properties": {
    "need": {
      "type": "string",
      "maxLength": 800,
      "description": "what must happen, in plain words"
    },
    "proof": {
      "type": "string",
      "maxLength": 400,
      "description": "what evidence closes the task, agreed before work starts"
    },
    "deadline": {
      "type": "string",
      "maxLength": 100,
      "description": "by when; ISO date or plain words"
    },
    "location": {
      "type": "string",
      "maxLength": 200,
      "description": "city or address in the Netherlands"
    },
    "synthetic": {
      "type": "boolean",
      "description": "true marks a test that must never be counted or executed"
    },
    "budget_cents": {
      "type": "integer",
      "minimum": 100,
      "description": "budget in euro cents"
    },
    "reply_channel": {
      "type": "string",
      "maxLength": 300,
      "description": "email or https URL where AstraNL may answer you"
    }
  },
  "additionalProperties": false
}
    arguments 43 lines
  • ground_astranl reads unknown 21h ago

    Get compact, source-linked real-world context for an LLM in ONE read-only call. Searches AstraNL public materials or tender records, or its protocol identity. Use source=public_tenders for tenders, materials for products; auto keeps domains separate. Returns record update times, fresh/stale/unknown labels, record disagreements, coverage gaps and ready-to-use context_text. Never books, contacts or pays anyone. Not a general web search: no match is not proof of absence; a cached price is not a quote. Optional astranl.reality-link.v2 profile checks exact source-record claims. It does not promote registry records to independently verified real-world facts. official.deadline on tender:TED-* records is checked live at the EU publisher (TED), budgeted and cached; unavailable means UNKNOWN.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 1600,
      "minLength": 2,
      "description": "Short subject, product keywords or identifier; all product keyword groups must match."
    },
    "claims": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id",
          "record_id",
          "predicate",
          "expected"
        ],
        "properties": {
          "id": {
            "type": "string",
            "maxLength": 64,
            "minLength": 1
          },
          "expected": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 600,
                "minLength": 1
              },
              {
                "type": "object",
                "required": [
                  "amount",
                  "currency"
                ],
                "properties": {
                  "amount": {
                    "type": "string",
                    "pattern": "^\\d{1,10}(\\.\\d{1,2})?$"
                  },
                  "currency": {
                    "type": "string",
                    "pattern": "^[A-Z]{3}$"
                  }
                },
                "additionalProperties": false
              }
            ]
          },
          "predicate": {
            "enum": [
              "record.title",
              "record.brand",
              "record.listed_price",
              "record.stock_reported",
              "record.closing_date",
              "reality.stock_available",
              "reality.delivery_by",
              "reality.suitable_for",
              "official.deadline"
            ],
            "type": "string"
          },
          "record_id": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
          }
        },
        "additionalProperties": false
      },
      "maxItems": 16,
      "minItems": 1,
      "description": "v2 only. Each claim names a record id from a previous result, a predicate and the expected value."
    },
    "source": {
      "enum": [
        "auto",
        "materials",
        "public_tenders",
        "protocol_identity",
        "all"
      ],
      "type": "string",
      "default": "auto",
      "description": "v1: auto, materials, public_tenders, protocol_identity or all. v2 requires an explicit materials, public_tenders or protocol_identity."
    },
    "protocol": {
      "enum": [
        "astranl.reality-link.v2"
      ],
      "type": "string",
      "description": "Omit for the v1 context call. Set to astranl.reality-link.v2 together with claims to check typed claims against source records."
    },
    "budget_ms": {
      "type": "integer",
      "default": 750,
      "maximum": 1500,
      "minimum": 50
    },
    "max_items": {
      "type": "integer",
      "default": 6,
      "maximum": 12,
      "minimum": 1,
      "description": "v1 only; v2 looks up at most 12 records and refuses max_items."
    },
    "max_age_seconds": {
      "type": "integer",
      "default": 86400,
      "maximum": 604800,
      "minimum": 60
    }
  },
  "additionalProperties": false
}
    arguments 122 lines
  • ground_citation unknown 9d ago

    Check one scientific reference before you reuse or cite it, with ONE call. Give a DOI. AstraNL reads the Crossref work record and every Crossref notice that updates it, the OpenAlex retraction flag and the Europe PMC publication types and retraction, erratum and concern links, and returns a status: RETRACTION_NOTICE_FOUND, EXPRESSION_OF_CONCERN_FOUND, CORRECTION_NOTICE_FOUND, NO_NOTICE_IN_CHECKED_SOURCES or NOT_FOUND_IN_CHECKED_SOURCES, with each notice DOI, type and date, the source URLs and the observation time. Every fresh answer carries a SHA-256 digest sealed with the AstraNL moment seal and an AstraLock event id you can check later with verify_astranl. Limits: registry data at the observed time, never a judgement of the science; NO_NOTICE_IN_CHECKED_SOURCES means only these three registries; answers are cached for 24 hours. Never contacts authors or publishers. Writes (why the tool is not read-only): each fresh answer, not one served from the 24 hour cache, appends one event to the public AstraLock log with the DOI, the digest and the status, so the answer can be verified later, and stores the answer in an AstraNL database table (citation_groundings) that serves the cache and counts the budget; the row names only the door (mcp), nothing about the caller. Live budget: 300 fresh reads a day across all MCP callers; after that only cached answers, status DAILY_LIVE_BUDGET_SPENT. Logging: every MCP call is journaled with the tool name, outcome, argument length, caller class (external, probe, crawler, self), a SHA-256 hash of the caller network /24 and the client family; for demand statistics also the first 160 characters of a query, question, title or id argument and the user-agent; never the address itself, other arguments or an account.

    mcp-tool

    {
  "type": "object",
  "required": [
    "doi"
  ],
  "properties": {
    "doi": {
      "type": "string",
      "maxLength": 300,
      "minLength": 7,
      "description": "the DOI of the work, bare or as a doi.org link, e.g. 10.1038/s41593-021-00895-5"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • order_materials unknown never probed

    Turn an AstraNL estimate into draft purchase lists for a project, one list per store and wave, and hand them to the project administrator. Needs the project agent key (agk_...) as X-Agent-Key on the connection; the estimate tools use the connection key, so use a separate connection. Read-only actions: me, case, estimate_links, list, order_status (reads an existing order record, it never places one). Actions that write: import_estimate (creates draft lists) and finish_list (sends one draft for approval). Required fields by action: me: none; case: project_id; import_estimate: project_id, estimate_case_id, estimate_token, idempotency_key; estimate_links: project_id; list: project_id, list_id; finish_list: project_id, list_id, list_revision, version, idempotency_key; order_status: project_id, order_id. Typical order: import_estimate, then list for each list_id, then finish_list with the revision and version read. The estimate must be RELEASED after review and must carry a material order plan, otherwise import_estimate answers a failure and writes nothing. If a write answers outcome_unknown, repeat the same call with the SAME idempotency_key; never use a new key. A project administrator approves the exact list. Nothing is ordered, approved or paid by this tool. A 202 means accepted for work, not completed.

    mcp-tool

    {
  "type": "object",
  "required": [
    "action"
  ],
  "properties": {
    "action": {
      "enum": [
        "me",
        "case",
        "import_estimate",
        "estimate_links",
        "list",
        "finish_list",
        "order_status"
      ],
      "type": "string",
      "description": "what to do; see the tool description for the fields each action takes"
    },
    "list_id": {
      "type": "string",
      "pattern": "^PL-[0-9a-f]{32}$",
      "description": "a purchase list id, PL-..."
    },
    "version": {
      "type": "integer",
      "minimum": 0,
      "description": "the current_version of the list as read"
    },
    "order_id": {
      "type": "string",
      "pattern": "^PI-[0-9a-f]{32}$",
      "description": "an order intent id, PI-..."
    },
    "project_id": {
      "type": "string",
      "pattern": "^PRJ-[A-Z0-9-]{1,80}$",
      "description": "the project case id, PRJ-..."
    },
    "list_revision": {
      "type": "integer",
      "minimum": 0,
      "description": "the revision of the list as read"
    },
    "estimate_token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{1,256}$",
      "description": "the token of that estimate case, from estimate_case_create"
    },
    "idempotency_key": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{8,80}$",
      "description": "8 to 80 letters, digits, - or _; the same key replays the same answer"
    },
    "estimate_case_id": {
      "type": "string",
      "pattern": "^ESTREQ-[0-9]{8}-[0-9a-f]{8}$",
      "description": "the estimate case id, ESTREQ-YYYYMMDD-xxxxxxxx"
    }
  },
  "additionalProperties": false
}
    arguments 62 lines
  • estimate_case_video unknown never probed

    Video action=create takes one base64 file up to 250 MiB and reuses the connection agent key (X-Agent-Key header of the MCP connection; get one free with POST https://astranl.com/api/agents/register). action=status takes intake_id and its token only. After case creation, use case_id and case_token with estimate_case_status. Video and case tokens are distinct.

    mcp-tool

    {
  "type": "object",
  "required": [
    "action"
  ],
  "properties": {
    "file": {
      "type": "object",
      "required": [
        "name",
        "data_base64"
      ],
      "properties": {
        "name": {
          "type": "string",
          "pattern": "^[A-Za-z0-9][A-Za-z0-9_. -]{0,119}$"
        },
        "data_base64": {
          "type": "string",
          "maxLength": 349525336,
          "minLength": 4
        }
      },
      "additionalProperties": false
    },
    "text": {
      "type": "string",
      "maxLength": 5000
    },
    "token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 256,
      "minLength": 1
    },
    "action": {
      "enum": [
        "create",
        "status"
      ],
      "type": "string"
    },
    "language": {
      "enum": [
        "en",
        "nl",
        "uk",
        "pl",
        "de",
        "fr",
        "es",
        "tr",
        "ar",
        "ro",
        "it"
      ],
      "type": "string",
      "default": "nl"
    },
    "postcode": {
      "type": "string",
      "maxLength": 20
    },
    "intake_id": {
      "type": "string",
      "pattern": "^VID-[0-9]{8}-[0-9a-f]{10}$"
    },
    "house_number": {
      "type": [
        "string",
        "integer"
      ]
    },
    "contact_email": {
      "type": "string",
      "maxLength": 254
    },
    "requester_kind": {
      "enum": [
        "agent"
      ],
      "type": "string",
      "default": "agent"
    },
    "speech_language": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$"
    }
  },
  "additionalProperties": false
}
    arguments 91 lines
  • record_counterparty_check changes data unknown never probed

    Make a result of check_counterparty_nl verifiable by others: records its digest in the AstraNL signed public log and returns a reference that a colleague, approver or auditor can check later with verify_astranl, without trusting AstraNL. Works only for a check AstraNL produced in the last 48 hours. The public record holds no name, number or address of the checked party. Calling it again returns the same reference.

    mcp-tool

    {
  "type": "object",
  "required": [
    "check_id"
  ],
  "properties": {
    "check_id": {
      "type": "string",
      "maxLength": 40,
      "description": "the check_id returned by check_counterparty_nl, ASTRA-K- and 16 characters"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • verify_astranl reads unknown 18h ago

    Verify any AstraNL reference without a key. Returns two separate layers: integrity (payload hash, Ed25519 signature, Merkle inclusion, recomputed live) and claim (what exactly is attested, by whom, from which source, when, under which method, with which validity limits and current status VALID/EXPIRED/REVOKED/UNKNOWN). Integrity never implies the claim is true for your purpose; you apply your own acceptance rules. Tells you when to re-verify and how to consume a VALID receipt for a next action. Read-only, deterministic, no model in the path.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ref"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "maxLength": 64,
      "minLength": 4,
      "description": "Any AstraNL reference: action receipt ASTRA-A-..., policy receipt ASTRA-R-..., consumption ASTRA-C-..., log event alk_..., attestation att_/atr_..., ingress receipt RCPT-n"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • estimate_case_create unknown never probed

    Create a real estimate case through the public router. Reuses the connection X-Agent-Key (get one free with POST https://astranl.com/api/agents/register; the api_key is shown once; send it as the X-Agent-Key header of the MCP connection); requester_kind is agent. Save case_id and token securely. language selects human-client output, default nl. Duplicates do not return a token. Processing may be asynchronous.

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 20000,
      "minLength": 1
    },
    "language": {
      "enum": [
        "en",
        "nl",
        "uk",
        "pl",
        "de",
        "fr",
        "es",
        "tr",
        "ar",
        "ro",
        "it"
      ],
      "type": "string",
      "default": "nl"
    },
    "postcode": {
      "type": "string",
      "maxLength": 20
    },
    "house_number": {
      "type": [
        "string",
        "integer"
      ]
    },
    "contact_email": {
      "type": "string",
      "maxLength": 254
    },
    "requester_kind": {
      "enum": [
        "agent"
      ],
      "type": "string",
      "default": "agent"
    }
  },
  "additionalProperties": false
}
    arguments 52 lines
  • estimate_case_answer unknown never probed

    Submit human answers as a map from question ID to text. The public router validates, merges and queues an operator rerun; submission does not itself spawn processing. Requires the case token.

    mcp-tool

    {
  "type": "object",
  "required": [
    "case_id",
    "token",
    "answers"
  ],
  "properties": {
    "token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 256,
      "minLength": 1
    },
    "answers": {
      "type": "object"
    },
    "case_id": {
      "type": "string",
      "pattern": "^ESTREQ-[0-9]{8}-[0-9a-f]{8}$"
    },
    "version": {
      "type": "integer",
      "minimum": 1
    }
  },
  "additionalProperties": false
}
    arguments 28 lines
  • estimate_case_files unknown never probed

    Upload photos or plans as base64 contents, never local paths or URLs. Requires the case token. Public feature flag, type checks, sanitization and quotas apply: 10 files, 15 MiB each, 60 MiB per case. Upload acceptance does not prove incorporation into an existing estimate.

    mcp-tool

    {
  "type": "object",
  "required": [
    "case_id",
    "token",
    "files"
  ],
  "properties": {
    "files": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "data_base64"
        ],
        "properties": {
          "name": {
            "type": "string",
            "pattern": "^[A-Za-z0-9][A-Za-z0-9_. -]{0,119}$"
          },
          "data_base64": {
            "type": "string",
            "maxLength": 20971520,
            "minLength": 4
          }
        },
        "additionalProperties": false
      },
      "maxItems": 10,
      "minItems": 1
    },
    "token": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 256,
      "minLength": 1
    },
    "case_id": {
      "type": "string",
      "pattern": "^ESTREQ-[0-9]{8}-[0-9a-f]{8}$"
    }
  },
  "additionalProperties": false
}
    arguments 45 lines
  • check_material unknown 13h ago

    Check one building material in live Dutch store reality with ONE read-only call. Exact identity only: a GTIN with valid check digit, a store variant or the exact partner feed link; plain words return candidates you can check exactly next. Returns every offer of the same trade item with price incl. VAT, stock and read time per store (Bouwmaat, Hubo, Houtdirect through UCP search; partner shop feeds), the identical GTIN at other stores (verdict DIRECT_SUBSTITUTE, the only substitute named), the cheapest available offer, per source status and a sha256 digest. Limits: seller prices at read time, not a quote or delivery promise; delivery costs not included; NOT_FOUND covers only the sources listed. Never orders, pays or contacts anyone.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ref"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "maxLength": 600,
      "minLength": 1,
      "description": "a GTIN or EAN with valid check digit (e.g. 8710839100056), a Bouwmaat, Hubo or Houtdirect product link with ?variant=, a partner shop product link, store:variant (e.g. hubo:48564194312444), or plain words for candidates"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
_ try it over mcp 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 691bf56bc330a5db.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/691bf56bc330a5db/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/691bf56bc330a5db/badge.svg)](https://brick.blue/agent/691bf56bc330a5db?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 knowoff the mcp door
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.

_ also on astranl.com 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.