MCP server

Connect a client

Streamable HTTP, stateless, at /mcp. Point a client at it:

{
  "mcpServers": {
    "futbol-atlas": {
      "type": "http",
      "url": "https://futbolatlas.app/mcp"
    }
  }
}

The registry manifest is at /.well-known/mcp/server.json.

Transport and limits

Protocol

2026-07-28

Also served

2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05, 2024-10-07

Body cap

64 KiB

Rate limit

120 / 60s

The limits are stated so they are a published rule rather than a surprise. A caller over the rate limit receives 429 with the standard headers saying when to retry; a body over the cap receives 413. Neither fails silently. Any method other than POST and OPTIONS receives 405 with Allow, and that refusal points back at this page.

Tools it serves

8 tools, listed as the server declares them. Every one returns typed structuredContent against a published outputSchema.

• search

  Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. Text match, weighted by where the token hits (name 3, tags 2, content 1 per query token), plus a centrality bonus of up to 0.9 for objects that other objects point at. That bonus is why two hits can share matched_fields and still score differently: the decimal is inbound edges, not text relevance. Use this whenever you have a question rather than an id, then follow up with get_entity.

  Arguments: query, limit (optional)

• get_entity

  Fetch one knowledge object by id, with its claims and the sources each claim cites. Use this once search, answer or get_topic has given you an id. An unknown id is not a dead end: the answer names near-miss ids you can retry with.

  Arguments: id

• get_topic

  List the knowledge objects carrying a tag (topics are content-backed tags). Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see which tags exist. An unknown tag comes back with the topics that do exist, so a miss still moves you forward.

  Arguments: tag

• answer

  Answer a question from the corpus. Returns the matched object's claims with sources and confidence — never an unsourced answer. Use this when the user asked a question in words; use search when you want to see the candidates yourself.

  Arguments: question

• get_sources

  The instance's whole source registry, or just the sources cited by one object — each with its evidence tier, reliability and access date. Use this when you need the registry entry behind a citation, or the whole registry to judge the corpus before trusting it; get_entity already tells you which sources a claim cites.

  Arguments: object_id (optional)

• get_related

  Graph neighbours of an object: outgoing and incoming relations, each with its relation type. Use this after get_entity to widen an answer with adjacent objects. It walks one hop from an id you already have — use search when you have a question and no starting object.

  Arguments: id

• get_latest

  Most recently verified knowledge objects (freshness signal). Use this to judge how current the corpus is, or to see what changed since you last read it. It ranks by verification date and ignores your topic entirely — use search or get_topic when you want objects that are relevant rather than recent.

  Arguments: limit (optional)

• get_overview

  Corpus overview: what this instance knows, counts by type, published tags, freshness. Use this first when you land here and do not yet know whether this corpus can answer your question.

  Takes no arguments.

If you are not using MCP

The same corpus is served as plain files. The agent interface lists every machine surface this build emits.