Statos MCP Server
Summary: This server exposes Statos's market-measurement and admin tools to AI assistants.
List mispriced legs (
list_candidates): return current scanner candidates with fair odds/probability, edge %, consensus book count, and quoted-range reliability.Get per-match candidates (
get_match_candidates): fetch all priced legs for a specific fixture bymatch_id.Discover leagues (
list_leagues): list tracked soccer leagues, filter by continent or specialized-only, and get league IDs for filtering.Suppress markets (
suppress_market): admin kill switch to stop a league × market from being emitted for a time window.List suppressions (
list_suppressions): view currently active market-suppression windows.Unsuppress markets (
unsuppress_market): cancel an active suppression by ID to restore emission.
Note: the schema also lists legacy tools (list_picks, get_match_picks, get_account) that the README says were removed in v0.4.0; the current server exposes the candidate/suppression tools above.
Click on "Deploy 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., "@Statos MCP Server what are the best value picks for today's matches?"
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.
@statospro/mcp
A Model Context Protocol server that connects AI assistants — Claude Desktop, Claude Code, claude.ai — to a Statos instance.
Statos tracks football odds across ~54 bookmakers and looks for legs where one book's price disagrees with a devigged consensus of the books measured sharper than it. This package wraps that surface in an AI-friendly tool layer, so an assistant can answer "is anything mispriced today?" without you writing an HTTP call.
npx -y @statospro/mcp@latest --api-token <token>What this is not. Statos used to serve a goal model's predictions, and earlier versions of this package exposed them as
list_picks. That model was refuted on its own ledger — −0.13% ROI across 17,060 settled picks at a 71.5% hit rate, about as good as the market and losing the vig — and its endpoint was removed in Statos v1.44.0. What you get now is a market measurement, not a forecast: it reports that a price disagrees with other prices, never that an outcome is likely.
Tools
v0.4.0 — market surface.
Tool | Wraps |
|
|
|
|
|
|
|
|
|
|
|
|
Scopes are gone. Statos is single-tenant and authenticates with one static bearer token, so every tool is available to whoever holds it — including the three market-suppression tools, which stop a (league × market) being emitted for a window without a deploy. Treat the token accordingly.
Removed in v0.4.0
Tool | Why |
| Called |
| Same endpoint. Use |
| Called |
list_candidates is not a rename of list_picks. A pick carried
suggested_prob — a model's belief about a match. A candidate carries
fair_prob — what the sharp books collectively price. The names differ because
the numbers do: keeping them would invite an assistant to carry model-shaped
reasoning onto values that fail in a completely different way.
Related MCP server: kicktipp-agent
Quick start
1. Get the token
Statos is single-tenant. The token is whatever the server was configured with as
STATOS_API_TOKEN; there is no self-service key page. If you run the instance,
it is in your deployment environment.
2a. Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"statos": {
"command": "npx",
"args": ["-y", "@statospro/mcp@latest"],
"env": {
"STATOS_API_TOKEN": "<token>"
}
}
}
}Restart Claude Desktop. The tools appear in the tools picker.
2b. Claude Code
claude mcp add statos -- npx -y @statospro/mcp@latest --api-token <token>2c. Sandbox
claude mcp add statos-sandbox -- npx -y @statospro/mcp@latest \
--api-token <sandbox-token> \
--api-base https://api.sandbox.statos.proTool reference
list_candidates
The legs the scanner currently considers mispriced.
param | type | default | notes |
| string[] | — |
|
| number | — | Percent, so |
| boolean |
| Drop legs whose fair price was extrapolated. |
| integer | server default | Max 500. |
Each leg carries:
field | meaning |
| The price the edge was computed against. Betting elsewhere voids it. |
| The devigged sharp consensus. |
| How much longer the price is than fair, in percent. |
| Sharp books behind the fair price. Reconstruction error scales about |
|
|
| The scan row. Cite it so a bet traces back to the run that produced it. |
The response also carries run_id, strategy, scanned_at and price_basis,
so a slate can be reproduced later.
An empty list is the normal result. Most fixtures are priced about where the sharp consensus puts them; on a typical day the scanner finds a handful of legs out of a hundred-odd it can price, and often none.
get_match_candidates
Every leg priced for one fixture.
param | type | notes |
| integer | The |
list_leagues
Discover league IDs and names.
param | type | default | notes |
| string | — |
|
| boolean |
| Only |
| integer | 200 | Max 500. |
suppress_market / list_suppressions / unsuppress_market
suppress_market takes league_id (0 = all), market, and duration_hours;
list_suppressions takes nothing; unsuppress_market takes an id.
Configuration
Env var | CLI flag | Default | Notes |
|
| — | Required. |
|
|
| Point at |
Troubleshooting
401— the token does not match the server'sSTATOS_API_TOKEN, or was truncated on copy. Note the server rejects a token shorter than 32 characters outright, so a half-pasted value fails the same way a wrong one does.401: missing or malformed Authorization header— the env var isn't reaching the server process. Restart your MCP client after editing config.404onlist_candidates— the Statos instance predates v1.44.0 and has no/worklist. Upgrade the backend, or use@statospro/mcp@0.3.0against it.No candidates — usually a genuinely quiet day rather than a fault. Call
list_candidateswith no filters to confirm the scan itself returned something, and readscanned_atto check how fresh the sweep is.
Versioning
The package version is independent of the Statos API version. The server sends
User-Agent: @statospro/mcp/<version> so backend logs can correlate, and that
version is read from package.json rather than restated in code — the two had
drifted before.
Requirements
Node.js ≥ 20, and a Statos instance at v1.44.0 or later.
License
MIT — see LICENSE.
Available Tools
7 toolsget_accountA
Return the API-key holder's account info: email, role (silver/gold/diamond/admin), subscription status, and the effective role (trial-elevated while a trial is active). Useful for an AI assistant to explain what plan the user is on and which leagues they have access to. Read-only.
Inputs: no named parameters.
get_match_picksA
Fetch every suggestion the Statos engine has emitted for a single match. Useful for per-match analysis: 'what does Statos think about match X across every market?'. Returns the same BetSuggestion shape as list_picks but scoped to one match.
Inputs: match_id (required).
list_leaguesA
List the soccer leagues the Statos engine tracks (filtered to what the API-key holder's plan permits). Each league carries an id you can pass to list_picks for filtering, plus name, country, continent, and an is_specialized flag indicating leagues the engine biases toward. Useful for discovery: 'which European leagues can I see?' or 'show me the specialized leagues only'.
Inputs: limit, continent, specialized_only.
list_picksA
List Statos's current betting suggestions, optionally filtered by league, market type, minimum edge, or quality tier. Each pick carries the model's claimed probability, best available odds (where attached), implied edge, and a confidence label (low/medium/high). Picks are computed live from upcoming fixtures; volumes vary by day. Use this for 'what does Statos suggest today?' type queries.
Inputs: limit, markets, quality, league_id, +1 more.
list_suppressionsA
List the currently active market suppressions (the kill switches in effect). Read-only; same admin scope as suppress_market.
Inputs: no named parameters.
suppress_marketA
ADMIN kill switch: stop Statos emitting a (league × market) for a time window WITHOUT a deploy — e.g. during the World Cup if 'cards' starts firing 30% below claimed hit rate. Requires an admin key with the admin:market_suppressions scope. league_id 0 = all leagues. Reversible via unsuppress_market or expiry. Use sparingly.
Inputs: market_type (required), hours, reason, league_id.
unsuppress_marketA
Cancel an active market suppression by id, immediately restoring emission (within ~60s). Requires the admin:market_suppressions scope.
Inputs: id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct resource and action: account retrieval, suppression listing, pick listing, per-match pick retrieval, league listing, and suppression creation/cancellation. The only potential overlap (list_picks vs get_match_picks) is clearly differentiated by scope and description.
All tool names follow a consistent verb_noun pattern in snake_case (get_account, list_suppressions, list_picks, get_match_picks, list_leagues, suppress_market, unsuppress_market). Verb choice and structure are predictable throughout.
Seven tools is well-scoped for a betting suggestions server: read operations for account, leagues, and picks, plus admin suppression management. Each tool earns its place with no redundancy.
The server covers account info, discovery (leagues), picks retrieval (global and per-match), and a full suppression lifecycle (list, create, cancel). No obvious gaps exist for the stated purpose.
Maintenance
Related MCP Connectors
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Official Intrinio MCP server. US stock prices, options and fundamentals for AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks.2918 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceMCP server for kicktipp.com that enables AI assistants to view match data, leaderboards, and place bets through natural language.67 npm10MIT
- FlicenseNot gradedqualityDmaintenanceAn open-source MCP server that turns any AI assistant into a football data analytics and scouting platform, enabling natural language queries over 40+ stats, 20+ leagues, and 10,000+ players.1-

RapidOddsAPI MCPofficial
AlicenseAqualityCmaintenanceLive bookmaker odds from 100+ sportsbooks (AU, US, EU), arbitrage and value bet finders, live game results and player stats for AI assistants. Built on the official RapidOddsAPI Python SDK. Free tier available.5223 PyPIMIT