Football Atlas
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Football AtlasWhen can VAR intervene?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Football Atlas — MCP server
The Laws of the Game and world football's major competitions, every claim cited to primary sources
A remote MCP server over a curated knowledge graph. Every claim it returns is bound to a registered source: the tools hand back claims with their citations and a confidence value, so an agent can show its work instead of asserting.
Nothing to install. It is a hosted streamable-HTTP endpoint:
https://futbolatlas.app/mcpAdd it to a client
Claude Code
claude mcp add --transport http futbol-atlas https://futbolatlas.app/mcpClaude Desktop / any client reading mcpServers
{
"mcpServers": {
"futbol-atlas": {
"type": "streamable-http",
"url": "https://futbolatlas.app/mcp"
}
}
}No API key, no account, no auth. Read-only.
Check it answers, without any client at all:
curl -s https://futbolatlas.app/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'mcp-protocol-version: 2025-06-18' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Related MCP server: football-scraper-mcp
Tools
Eight, each with an outputSchema, each returning structuredContent.
tool | arguments | what it does |
| — | Corpus overview: what this instance knows, counts by type, published tags, freshness. Start here when you land and do not yet know whether this corpus can answer your question. |
|
| Full-text search over the knowledge graph. Accent- and apostrophe-insensitive, so query in the user's own words; every hit carries its relevance score and the fields it matched. |
|
| Answer a question from the corpus. Returns the matched object's claims with sources and confidence — never an unsourced answer. |
|
| Fetch one knowledge object by id, with its claims and the sources each claim cites. |
|
| List the knowledge objects carrying a tag (topics are content-backed tags). |
|
| Graph neighbours of an object: outgoing and incoming relations, each with its relation type. |
|
| The whole source registry, or just the sources cited by one object. Use it to judge the corpus before trusting it. |
|
| Most recently verified knowledge objects — a freshness signal. |
The intended path is get_overview → search or answer → get_entity
→ get_related. get_overview exists because an agent that has just
arrived needs to know whether this corpus can help before it spends a
call guessing.
What is in the corpus
knowledge objects | 141 |
registered sources | 132 |
published topics | 96 |
type | objects |
entity | 114 |
glossary | 12 |
faq | 7 |
guide | 5 |
comparison | 3 |
Subject matter: the seventeen Laws of the Game as the IFAB writes them, VAR protocol and its review categories, competition formats and qualification paths, offside, handball and the wording that decides them.
Questions it is built to answer
What exactly does Law 11 say about a player's position at the moment the ball is played?
When may VAR intervene, and when is it forbidden to?
How does a team qualify for the Champions League league phase?
What an answer actually looks like
A real call against the live endpoint — answer with
"when can VAR intervene" — returns this structuredContent, trimmed:
{
"answered": true,
"entity": {
"id": "var",
"name": "VAR (Video Assistant Referee)",
"evidence_tier": "primary",
"confidence": 0.94,
"last_verified": "2026-08-08",
"canonical_url": "https://futbolatlas.app/k/var"
},
"claims": [
{
"text": "The VAR may assist the referee only for a clear and obvious error or a serious missed incident in these match-changing categories: goal/no goal, penalty/no penalty, direct red card, and mistaken identity when the referee cautions or sends off the wrong player of the offending team.",
"sources": [{ "title": "Video Assistant Referee (VAR) protocol (Laws of the Game 2026/27)" }]
}
]
}Note what travels with the answer: the evidence tier, a confidence, the date it was last verified, and the source behind the claim — not as prose an agent has to parse, but as fields it can act on. An agent can decline to use a weak claim, or cite the primary source directly.
When the corpus cannot answer, answered is false. It does not
improvise, and the miss is recorded so the gap can be filled.
Machine-readable surfaces
The MCP endpoint is one of several. The same corpus is served as plain files an agent can read directly:
surface | what it is |
the index, as | |
the whole corpus in one file | |
every surface this instance publishes, with its content type | |
one JSON document per knowledge object | |
the source registry, in full | |
this server's manifest |
Each knowledge object has a human page and a machine twin at the same id, with a canonical URL that agrees across all of them.
Behaviour worth knowing before you integrate
POSTonly. Every other method answers405with anAllow: POST, OPTIONSheader.Rate limit: 120 requests per minute per client, counted in a shared store, published on every response as
RateLimit-Limit,RateLimit-RemainingandRateLimit-Reset(all three exposed via CORS). It fails open: if the store is unreachable the request is served.Malformed input gets a spec-correct JSON-RPC error —
-32700for unparseable bodies,-32602for an unknown tool — never an HTML error page.Request bodies are capped and validated before transport.
Privacy
No accounts, no cookies, no ads. Usage is measured in aggregate with daily-rotating hashed identifiers and a 200-day retention; raw IPs are never stored. Full policy: PRIVACY.md.
Provenance and licence
Knowledge content is CC-BY-4.0: use it, cite it. The source registry is
public precisely so a claim can be checked rather than trusted —
get_sources returns what any given claim rests on.
Claims carry an evidence tier and a last_verified date. Where the
evidence is weaker, the object says so rather than rounding up.
How it is built
Compiled and served by Citarium, an open-source framework for turning a knowledge graph into a website, an API, an MCP server and agent-readable files from a single source — under external evaluation, with the guardians and the falsification record in the open.
This repository is the server's public face: its manifest and its documentation. The corpus itself lives at futbolatlas.app.
This server cannot be installed
Maintenance
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables natural language querying of a football knowledge graph via Neo4j, generating Cypher queries and answers using LLMs, and also provides tools to build the graph from text.
- FlicenseNot gradedqualityDmaintenanceProvides tools to query football match data, odds, standings, and team statistics via natural language, integrating with the football-scraper-api.
- FlicenseBqualityBmaintenanceEnables access to live FotMob football data for fixture lookup, team and player research, match details, lineups, league discovery, and search-based entity lookup.76
- FlicenseNot gradedqualityDmaintenanceEnables natural language querying of football/soccer data via the API-Football service, providing access to leagues, teams, players, fixtures, standings, and statistics.3
Related MCP Connectors
Resolve, search and verify legal citations against the official sources, with provenance.
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
Citable retrieval across papers, books, patents, Wikipedia, and live social sources.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/citarium/futbolatlas-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server