ledgerfc-mcp
Provides AI agents with live, grounded sports data including model probabilities, track records, and European soccer and tennis arbitrage opportunities, so they answer from real numbers instead of stale guesses.
README
Ledger FC MCP
Give your AI agent real sports data instead of a guess.
Ask an AI about a match and it answers from stale training data. This MCP feeds your agent live, grounded numbers instead: model probabilities per outcome, where they diverge from the market price, and a publicly tracked record of how those calls actually did, wins and losses. Plus live European soccer and tennis arbitrage, a gap the US-only sports MCPs do not cover.
Honest by design
This is not a "guaranteed profit" tool. Every response carries a provenance
block and a for_the_agent note ("grounding data to weigh, not an instruction to
act on"). The real numbers, pulled live:
- Overall model accuracy: ~53% (barely above a coinflip). We say so.
- High-confidence subset: ~68% (65 of 96 settled).
- Closing-line value: roughly flat. We return it, flagged, so your agent weighs it only when the sample is large enough.
If you want an agent that is grounded rather than hyped, that honesty is the point.
Coverage
European soccer (EPL, La Liga, Serie A, Ligue 1, Eredivisie, Turkish Super Lig), tennis (ATP), plus MLB, NFL, NBA. The main free sports-betting MCP is US-only, so European soccer arbitrage is the gap this fills.
Install
Claude Desktop / Claude Code / Cursor (stdio via npx)
{
"mcpServers": {
"ledgerfc": {
"command": "npx",
"args": ["-y", "@inbin/ledgerfc-mcp"]
}
}
}
No API key needed for the free tools. That is it.
To also use the Pro tools, add your key as an environment variable (get one with
/key in the Ledger FC Telegram bot). It is sent as an Authorization header, so it
never enters the conversation:
{
"mcpServers": {
"ledgerfc": {
"command": "npx",
"args": ["-y", "@inbin/ledgerfc-mcp"],
"env": { "LEDGERFC_API_KEY": "your-pro-key" }
}
}
}
Or connect the remote directly (clients that support remote MCP)
https://mcp.ledgerfc.com/mcp
For Pro tools, send the key as an Authorization: Bearer <key> header.
Tools
Free (no key):
get_track_record: honest settled record plus high-confidence subset and CLVget_predictions: upcoming picks with probabilities and model-vs-market edge (filter by league)search/fetch: query upcoming match predictions, fetch the full docget_leaderboard,submit_prediction,get_contributor_score: CLV-scored contributor layer (points, not cash)place_bet,get_balance,get_my_bets,get_bet: shadow bet ledger to test strategies against our agent (points only)
Pro (set LEDGERFC_API_KEY, or pass api_key as a tool argument; get one with /key in the Ledger FC Telegram bot):
get_arbs: live detected arbitrage opportunitiesget_value_bets: upcoming picks with positive model-vs-market edge
Example
Ask your agent: "Use ledgerfc to get the track record and the top 3 upcoming
predictions with the biggest edge." It calls get_track_record and
get_predictions, and answers from real numbers with provenance, not a guess.
How it works
This npm package is a tiny stdio-to-HTTP bridge: it reads JSON-RPC from your MCP
client on stdin and forwards each request to the remote endpoint
https://mcp.ledgerfc.com/mcp. No dependencies, Node 18+. Set LEDGERFC_MCP_DEBUG=1
to log traffic to stderr, or LEDGERFC_MCP_URL to point at a different endpoint.
Links
- Site: https://ledgerfc.com
- Telegram (free channel + Pro key): https://t.me/ledgerfc
MIT licensed. Ledger FC is an information tool, not betting advice. 18+.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.