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+.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。