rapidoddsapi-mcp
MCP server for RapidOddsAPI that provides bookmaker odds, live scores, arbitrage and value bets to AI assistants. It supports querying sports, odds, results, and betting opportunities with credit-based usage.
README
rapidoddsapi-mcp
MCP server for RapidOddsAPI. Gives an AI assistant bookmaker odds, live scores, arbitrage and value bets.
Built on the official rapidoddsapi
Python SDK.
Setup
You need an API key from the dashboard.
Keys start with oa_.
Claude Desktop
Add this to claude_desktop_config.json:
{
"mcpServers": {
"rapidoddsapi": {
"command": "uvx",
"args": ["rapidoddsapi-mcp"],
"env": {
"RAPIDODDSAPI_API_KEY": "oa_your_api_key_here"
}
}
}
}
The config file lives at ~/Library/Application Support/Claude/ on macOS and
%APPDATA%\Claude\ on Windows. Restart Claude Desktop after editing it.
Anything else that speaks MCP
RAPIDODDSAPI_API_KEY=oa_your_api_key_here uvx rapidoddsapi-mcp
It speaks stdio.
Tools
| Tool | Credits |
|---|---|
list_sports(sport=) |
0 |
get_odds(sport, market_types=, bookmakers=) |
market_types x ceil(bookmakers / 5) |
get_results(sport, status=, include=) |
1 |
find_arbitrage(sport, market=, bookmakers=, min_profit=, stake=) |
ceil(bookmakers / 5) |
find_value_bets(sport, market=, bookmakers=, min_edge=, devig=) |
ceil(bookmakers / 5) |
Credits are charged only when games come back, so a query that matches nothing is free. Every response ends with what it cost and what is left.
Credits
The free tier is 250 credits for the life of the account, with no monthly reset, so the defaults are deliberately narrow:
- A sport is always required. There is no way to request every sport at once.
- Bookmakers default to five, one credit group, chosen for the sport's region.
- Market types default to one.
That makes a typical question cost 1 credit. Both arguments multiply, so asking for nine market types across eighteen bookmakers is 36. The tool descriptions say so, which is what keeps the model from doing it uninvited.
find_arbitrage and find_value_bets default to ten bookmakers, 2 credits,
because both need books that disagree and five rarely spread far enough.
Markets
find_arbitrage and find_value_bets handle any market whose bets have two
sides: head_to_head and its period variants, soccer's draw_no_bet, totals,
handicaps, team totals and player props. Each line is its own bet, so a totals
market can return several results for one game.
Three-way markets return an error explaining why rather than an empty list, since "nothing found" would read as "no opportunities".
find_value_bets takes devig for where the fair price comes from. The
default, "all", de-vigs every bookmaker fetched and averages the result,
which needs no view on which book is sharp. Naming one, devig="Pinnacle",
measures every other book against that one instead: tighter, but only on
markets that book prices. A consensus needs four bookmakers on the same line,
so on thin markets naming a book finds bets that averaging cannot.
Market keys vary by sport. list_sports(sport) returns the valid ones and
costs nothing.
Bookmakers
Names are odds feeds, not brands. Many brands share one feed and quote
identical prices, so Ladbrokes covers Neds and Betmakers covers the 26
brands running on it. A brand name that is not a feed returns nothing.
Development
pip install -e ".[dev]"
pytest
ruff check .
mypy src/rapidoddsapi_mcp
Links
License
MIT
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.