polymarket-mcp
Enables AI assistants to query Polymarket prediction markets and analyze market data through the MCP interface.
README
Polymarket MCP Server
A Model Context Protocol (MCP) server for Polymarket's Gamma Markets API.
This provides access to Polymarket's prediction markets and market data through standardized MCP interfaces, allowing AI assistants to query market data and analyze prediction markets.
Features
-
[x] Market and Event data access
- [x] List all available markets and events with extensive filtering options
- [x] Get detailed market and event information
- [x] Search markets by keyword
- [x] Get order book data
- [x] View recent trades
- [x] Get historical market data
-
[x] Docker containerization support
-
[x] Provide interactive tools for AI assistants
The list of tools is configurable, so you can choose which tools you want to make available to the MCP client. This is useful if you don't use certain functionality or if you don't want to take up too much of the context window.
Usage with Claude Desktop
Docker Setup
To use the containerized server with Claude Desktop, add this to your Claude Desktop configuration:
{
"mcpServers": {
"polymarket": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "GAMMA_API_URL",
"-e", "GAMMA_REQUIRES_AUTH",
"polymarket-mcp-server"
],
"env": {
"GAMMA_API_URL": "https://gamma-api.polymarket.com",
"GAMMA_REQUIRES_AUTH": "false"
}
}
}
}
Note: You'll need to build the Docker image first with
docker build -t polymarket-mcp-server .
UV Setup (Alternative Method)
If you prefer not to use Docker, you can use uv to run the server directly:
- Create and configure a
.envfile in the project root directory:
# Copy the template
cp .env.template .env
# Edit the file to add your configuration
nano .env
Example .env content:
# Polymarket Gamma API Configuration
GAMMA_API_URL=https://gamma-api.polymarket.com
GAMMA_REQUIRES_AUTH=false
- Add the server configuration to your Claude Desktop configuration:
{
"mcpServers": {
"polymarket": {
"command": "/usr/local/bin/uv", // Use the full path to your uv installation
"args": [
"run",
"-m", "polymarket_mcp_server.main"
],
"cwd": "<full path to polymarket-mcp directory>",
"env": {
"GAMMA_API_URL": "https://gamma-api.polymarket.com",
"GAMMA_REQUIRES_AUTH": "false"
}
}
}
}
Note: If you see
Error: spawn uv ENOENTin Claude Desktop, you may need to specify the full path touvor set the environment variableNO_UV=1in the configuration.
Development
Contributions are welcome! Please open an issue or submit a pull request if you have any suggestions or improvements.
This project uses uv to manage dependencies. Install uv following the instructions for your platform:
curl -LsSf https://astral.sh/uv/install.sh | sh
You can then create a virtual environment and install the dependencies with:
uv venv
source .venv/bin/activate # On Unix/macOS
.venv\Scripts\activate # On Windows
uv pip install -e .
Environment Variables Support
The server loads environment variables from a .env file in the project root directory if present. Copy .env.template to .env and adjust the values as needed.
Project Structure
The project has been organized with a src directory structure:
polymarket-mcp/
├── src/
│ └── polymarket_mcp_server/
│ ├── __init__.py # Package initialization
│ ├── server.py # MCP server implementation
│ └── main.py # Main application logic
├── Dockerfile # Docker configuration
├── .dockerignore # Docker ignore file
├── .env.template # Template for environment variables
├── pyproject.toml # Project configuration
└── README.md # This file
Testing
The project includes a comprehensive test suite that ensures functionality and helps prevent regressions.
Run the tests with pytest:
# Install development dependencies
uv pip install -e ".[dev]"
# Run the tests
pytest
# Run with coverage report
pytest --cov=src --cov-report=term-missing
Tests are organized into:
- Server functionality tests
- Main application tests
- Error handling tests
When adding new features, please also add corresponding tests.
Available Tools
| Tool | Category | Description |
|---|---|---|
get_markets |
Market Data | Get a list of all available markets with comprehensive filtering options |
get_market_by_id |
Market Data | Get detailed information about a specific market |
get_order_book |
Market Data | [EXPERIMENTAL] Get the current order book for a market |
get_recent_trades |
Market Data | [EXPERIMENTAL] Get latest trades for a market |
get_market_history |
Market Data | [EXPERIMENTAL] Get historical market data |
search_markets |
Market Data | Search for markets by keyword using slug filtering |
get_events |
Event Data | Get a list of all available events with comprehensive filtering options |
get_event_by_id |
Event Data | Get detailed information about a specific event |
License
MIT
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。