polymarket-mcp
AI-agent ready FastMCP server for Polymarket market discovery, wallet analytics, and public CLOB data, providing a read-only interface for querying markets, wallets, and order books.
README
polymarket-mcp
AI-agent ready FastMCP server for Polymarket market discovery, wallet analytics, and public CLOB data.
polymarket-mcp gives MCP clients a typed, read-only interface for asking questions like:
- "Find active markets about inflation and summarize liquidity."
- "Inspect this wallet's current positions and recent activity."
- "Compare order book depth, midpoint, and spread for these outcome tokens."
- "Pull historical prices so an agent can reason about market movement."
This project is intentionally read-only in 0.1.x. It does not place trades, sign orders, manage keys, or require wallet credentials.
Package identities
| Purpose | Value |
|---|---|
| PyPI distribution | polymarket-mcp-server |
| Python package | polymarket_mcp |
| CLI command | polymarket-mcp |
| Docs | https://polymarket-mcp.readthedocs.io/en/latest/ |
Why agents use it
- Typed outputs reduce brittle prompt parsing and normalize inconsistent upstream JSON.
- Tool docstrings are written for LLM routing, so agents can choose the right surface quickly.
- Namespaces keep workflows clear:
gammafor discovery,datafor wallets,clobfor live market microstructure. - Real MCP end-to-end tests exercise both in-process client sessions and subprocess stdio transport.
- No authenticated trading actions are exposed, which keeps exploratory agents inside a safer read-only boundary.
Agent workflow
flowchart LR
Agent["AI agent / MCP client"] --> MCP["polymarket-mcp"]
MCP --> Gamma["gamma: discover markets and events"]
MCP --> Data["data: inspect wallets and trades"]
MCP --> Clob["clob: read books, quotes, history"]
Gamma --> GAPI["Gamma API"]
Data --> DAPI["Data API"]
Clob --> CAPI["Public CLOB API"]
Tool surfaces
| Surface | Agent job | Example outputs |
|---|---|---|
gamma |
discover and inspect markets/events | market metadata, event details, tags |
data |
analyze public wallet behavior | positions, activity, trades |
clob |
reason about live prices and liquidity | books, quotes, midpoint, spread, history |
Install
pip install polymarket-mcp-server
polymarket-mcp
Run ephemerally with uvx:
uvx --from polymarket-mcp-server polymarket-mcp
MCP client config
Use this stdio entry in an MCP client configuration:
{
"mcpServers": {
"polymarket": {
"command": "uvx",
"args": ["--from", "polymarket-mcp-server", "polymarket-mcp"]
}
}
}
Local development
This repository uses PDM.
pdm install -G dev
pdm install -G docs
pdm run mcp-inspect # inspect the composed MCP surface
pdm run mcp-run # run the stdio MCP server
pdm run test # run pytest
pdm run test-mcp # run real MCP client/server e2e tests
pdm run all # tests + strict docs + MCP inspect
Run the package entrypoint directly:
pdm run python -m polymarket_mcp.server
Safety model
polymarket-mcp is built for research, monitoring, and agent reasoning over public data. It intentionally excludes:
- private key handling
- authenticated trading
- order placement or cancellation
- wallet mutation
- custody or signing flows
If you build a trading layer on top, keep it separate from this read-only server and require explicit human authorization.
Project layout
src/polymarket_mcp/
models/ Pydantic domain and tool I/O models
services/ upstream API normalization layers
servers/ FastMCP tool and resource surfaces
server.py composed parent MCP server
tests/ unit and MCP end-to-end coverage
docs/ Sphinx documentation
Documentation
- Hosted docs: https://polymarket-mcp.readthedocs.io/en/latest/
- Docs source:
docs/using native Sphinx reStructuredText - Local build:
pdm run docs - Local preview:
pdm run docs-serve
Release notes
Releases publish from Git tags through GitHub Actions trusted publishing. PyPI trusted publishing is configured for pr1m8/polymarket-mcp, workflow release.yml, environment pypi.
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。