vela

endpoint

https://vela.study/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 vela live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is vela free to use?

Yes — the hub reached it with no key and no payment.

What tools does vela have?

10 tools: vela.library.reading_list, vela.corpus.witness, vela.magazine.sequence_path, vela.research.get_study, vela.corpus.ground_claim, vela.corpus.query, vela.magazine.relation_floor, vela.research.list_studies, ….

Is vela 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.

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.

• vela.corpus.query reads open 41d ago

  Ask the corpus by COORDINATE rather than keyword. Filter works by axis weights (e.g. religion ∈ {T,s} AND work ∈ {T,s} returns the God-and-Work source set across genres), controlled themes, qualities/emotions, genre, and free text. Returns card metadata: the one-line claim, themes, coordinates, qualities. FREE and read-only. [capability: library-extraction-cards · mirrors: POST /api/corpus/query]

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "axes": {
        "type": "object",
        "description": "Axis → allowed weights. ALL listed axes must match. e.g. {\"religion\":[\"T\",\"s\"],\"work\":[\"T\",\"s\"]}",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "text": {
        "type": "string",
        "description": "Substring match over title / author / one-line claim."
      },
      "genre": {
        "type": "string"
      },
      "limit": {
        "type": "integer",
        "default": 50,
        "maximum": 200,
        "minimum": 1
      },
      "topic": {
        "type": "string",
        "default": "being-human",
        "description": "Coordinate system to query (topic_configs.slug)."
      },
      "offset": {
        "type": "integer",
        "default": 0,
        "maximum": 9007199254740991,
        "minimum": 0
      },
      "themes": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Cards citing ANY of these controlled themes."
      },
      "qualities": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Cards carrying ANY of these qualities (emotions, for being-human)."
      },
      "include_passages": {
        "type": "boolean",
        "default": false,
        "description": "Include theme-anchored passage pointers."
      }
    }
  }

  arguments 62 lines copy
• vela.magazine.relation_floor reads open 42d ago

  Whether a magazine's corpus can support the adaptive promise its pages render. Reports, per property, each relational dimension's fill AND its separating power — a field present on every piece with one distinct value carries no information, so fill rate alone is misleading. Read-only. [capability: adaptive-magazine-engine · mirrors: npm run magazine:relation-floor]

  mcp-tool

  123456789101112

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "property": {
        "type": "string",
        "maxLength": 64,
        "minLength": 1,
        "description": "Restrict to one property id; omit for every property with published pieces."
      }
    }
  }

  arguments 12 lines copy
• vela.research.list_studies reads open 42d ago

  List FieldStation research ideas as a library-kit DiscoveryDTO. Each card is a study we can support, not a running participant surface. The honesty gate (limitations, readiness, doNotClaim) is enforced by research:catalog-check — this tool publishes that same file. FREE and read-only. Presence is gated; truth is not. [capability: study-catalogue · mirrors: GET /api/research/studies]

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• vela.corpus.describe_topic reads open 42d ago

  Describe ONE topic in full — its axes and their operative definitions, its complete controlled theme and quality vocabularies, plus the vocabulary actually IN USE across the corpus with counts. The declared vocabulary and the used vocabulary are different facts; this returns both. FREE and read-only. [capability: topic-coordinate-systems · mirrors: GET /api/corpus/topics/:slug]

  mcp-tool

  12345678910

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "topic": {
        "type": "string",
        "default": "being-human"
      }
    }
  }

  arguments 10 lines copy
• vela.corpus.list_topics reads open 42d ago

  List the coordinate systems the corpus can be queried through — each with its thesis, axes, and controlled vocabularies. Call this before vela.corpus.query to learn what axes and themes exist. FREE and read-only. [capability: topic-coordinate-systems · mirrors: GET /api/corpus/topics]

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• vela.library.reading_list reads unknown never probed

  The reading list an emotion or theme page shows: books with one-line claims and a short attributed passage (≤300 chars). Exactly one of emotion or theme. FREE and read-only. Every url carries ?ref=mcp for citation arrival measurement. [capability: library-extraction-cards · mirrors: GET /api/corpus/reading-list]

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "limit": {
        "type": "integer",
        "default": 24,
        "maximum": 24,
        "minimum": 1
      },
      "theme": {
        "type": "string",
        "description": "Controlled theme slug (e.g. desire). Mutually exclusive with emotion."
      },
      "emotion": {
        "type": "string",
        "description": "Emotion primary slug (e.g. grief). Mutually exclusive with theme."
      }
    }
  }

  arguments 20 lines copy
• vela.corpus.witness reads unknown 42d ago

  Literary Witness Rail (ASN-1577): return passages and one-line claims from Vela's 762-work corpus that illuminate the given themes and/or emotions. Designed for frame-family profile pages — PersonFrame × ProblemFrame × ConditionFrame — to add an inside-out layer (what writers who lived this say) alongside the outside-in portrait the frame join produces. Results carry evidence_grade 'T1' (single-extractor) until PRN-282 lands. FREE for claims; costs one embedding for the passage path. [capability: literary-witness · mirrors: GET /api/vela/witness]

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "axes": {
        "type": "object",
        "description": "Axis weight filters for claims only — same format as vela.corpus.query (e.g. {work:[\"T\",\"s\"]}).",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "themes": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "description": "Controlled themes from Vela's vocabulary (e.g. 'fairness', 'recognition')."
      },
      "emotions": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "description": "Emotions to match (e.g. 'shame', 'betrayal', 'grief'). At least one of themes or emotions is required."
      },
      "max_claims": {
        "type": "integer",
        "default": 3,
        "maximum": 8,
        "minimum": 1,
        "description": "Max one-line claims to return (default 3)."
      },
      "max_passages": {
        "type": "integer",
        "default": 5,
        "maximum": 10,
        "minimum": 1,
        "description": "Max passages to return (default 5)."
      },
      "problem_slug": {
        "type": "string",
        "description": "ProblemFrame entity slug (echoed in response; reserved for frame_tags[] pre-cache after PA-1153 ID-freeze)."
      },
      "condition_slug": {
        "type": "string",
        "description": "ConditionFrame entity slug (same reservation as problem_slug)."
      }
    }
  }

  arguments 57 lines copy
• vela.magazine.sequence_path reads unknown 42d ago

  Ask what this magazine would actually give a reader who said they wanted these things. Returns the REAL sequenced path with the rationale for each piece — the same core the anonymous intake calls, not a preview. Read-only: writes nothing and records no signal. [capability: adaptive-magazine-engine · mirrors: POST /api/magazine/start-path]

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "forms": {
        "type": "array",
        "items": {
          "type": "string",
          "maxLength": 64,
          "minLength": 1
        },
        "maxItems": 12,
        "description": "Article forms to steer by. At least one of emotions/forms is required."
      },
      "limit": {
        "type": "integer",
        "maximum": 12,
        "minimum": 1,
        "description": "Pieces to return (default 4)."
      },
      "emotions": {
        "type": "array",
        "items": {
          "type": "string",
          "maxLength": 64,
          "minLength": 1
        },
        "maxItems": 12,
        "description": "Emotions the reader is steering by."
      },
      "property": {
        "type": "string",
        "maxLength": 64,
        "minLength": 1,
        "description": "Property id; defaults to vela."
      }
    }
  }

  arguments 38 lines copy
• vela.research.get_study reads unknown never probed

  One FieldStation study as a library-kit ProfileDTO plus the raw StudyRecord. Unknown id is an error. FREE and read-only. [capability: study-catalogue · mirrors: GET /api/research/studies/:id]

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "id"
    ],
    "properties": {
      "id": {
        "type": "string",
        "minLength": 1,
        "description": "Catalogue id, e.g. S-01."
      }
    }
  }

  arguments 14 lines copy
• vela.corpus.ground_claim reads unknown never probed

  Ground a claim in the corpus: hybrid semantic + theme retrieval over real passages, returning citations with source, passage code, scores, and a SHORT snippet. Use to check whether the corpus supports, complicates or is silent on an assertion. COSTS a small amount (one embedding per call). [capability: corpus-ingestion-dual-grade · mirrors: internal — lib/audit/retrieve.ts]

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "claim"
    ],
    "properties": {
      "claim": {
        "type": "string",
        "minLength": 3,
        "description": "The claim to ground."
      },
      "limit": {
        "type": "integer",
        "default": 8,
        "maximum": 20,
        "minimum": 1
      }
    }
  }

  arguments 20 lines copy

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

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.