What are the prerequisites to run mcp-odds-api?
You need Python 3.10 or higher, a valid OddsAPI key (request one at https://the-odds-api.com/account/), and the `uv` package manager installed.
@marcoeg
基本信息
MCP server for odds-api
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-odds-api": {
"command": "uvx",
"args": [
"--env-file",
"/path/to/.env",
"mcp-odds-api",
"--transport",
"sse",
"--port",
"9090"
]
}
}
}- Get in-play and forthcoming events (matches).
- Get odds for all forthcoming events (matches) for selected betting markets.
- Get odds for a specific event (match) for selected betting markets.
mcp-odds-api is a minimalist Model Context Protocol (MCP) server that provides tools to interact with the OddsAPI. It is designed for developers who want to retrieve sports betting odds and events within an MCP-compatible client (e.g., Claude Desktop). The server uses environment variables to limit queries to specific regions and a single sport, and supports both SSE and STDIO transport protocols.
Configure the server by adding a JSON entry to the Claude Desktop config file (claude_desktop_config.json), providing the ODDS_API_KEY, ODDS_API_REGIONS, and ODDS_API_SPORT environment variables. Alternatively, run a standalone SSE server with uvx --env-file /path/to/.env mcp-odds-api --transport sse --port 9090. The server exposes three tools: get_events, get_odds, and get_event_odds.
get_events tool for in-play and forthcoming eventsget_odds tool for odds across all forthcoming eventsget_event_odds tool for odds on a specific eventget_events toolget_oddsget_event_oddsYou need Python 3.10 or higher, a valid OddsAPI key (request one at https://the-odds-api.com/account/), and the `uv` package manager installed.
Edit the Claude Desktop configuration file (on macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`; on Windows: `%APPDATA%/Claude/claude_desktop_config.json`) and add an entry under `mcpServers` with the correct `command`, `args`, and `env` variables (`ODDS_API_KEY`, `ODDS_API_REGIONS`, `ODDS_API_SPORT`).
The server supports both SSE (Server-Sent Events) and STDIO transports. You can start the server with SSE by passing `--transport sse --port 9090`.
It provides three tools: `get_events` (returns in-play and forthcoming events), `get_odds` (returns odds for all forthcoming events for selected markets), and `get_event_odds` (returns odds for a specific event for selected markets).
Create a `.env` file in the project root with `ODDS_API_KEY`, `ODDS_API_REGIONS`, and `ODDS_API_SPORT`, or pass them directly in the Claude Desktop configuration's `env` block.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
评论