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.
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.