polymarket-mcp
MCP server for Polymarket prediction markets enabling query of markets, events, narratives, arbitrage, and more via MCP or HTTP.
README
Polymarket MCP Server
<!-- mcp-name: polymarket-mcp -->
Model Context Protocol server for Polymarket prediction markets. v0.3.0
Query Polymarket markets, events, narratives, arbitrage opportunities, and more — from any MCP-compatible client (Claude Desktop, OpenClaw, Cursor, etc.) OR via HTTP REST.
Zero dependencies. No API key required. MIT license.
Quick Start
Option A: MCP (recommended)
Option B: HTTP (for curl/web/dashboards)
Available Tools
| Tool | Description |
|---|---|
| top_markets | Top markets by volume (24h or total) with formatted prices |
| search_markets | Client-side keyword search across title+description |
| get_market | Detailed market info by slug |
| top_movers | Biggest price movers with price formatting |
| list_events | List events with optional child market details |
| market_narratives | Cluster events by theme/narrative with volume analysis |
| detect_volume_spikes | Find markets with unusual 24h volume spikes |
| find_arbitrage | Discover Yes+No != 100% opportunities |
| market_summary | Comprehensive ecosystem snapshot |
Changelog
v0.3.0 (2026-06-26)
- HTTP mode: --http PORT starts a REST API at /health, /tools, /call/{tool_name}
- HTML status page: GET / shows a human-readable dashboard
- CORS headers: All endpoints support cross-origin requests
v0.2.0 (2026-06-26)
- Smart price formatting (Yes 52¢ / No 48¢)
- Proper client-side search
- Retry logic (429, 502, 503, 504)
- Connection resilience
Technical Details
- Protocol: JSON-RPC 2.0 over stdio (MCP) OR HTTP REST
- Dependencies: Zero (Python standard library only)
- API: Polymarket Gamma API (public, no key needed)
- Python: 3.7+
- License: MIT
Configuration with Claude Desktop
Add to claude_desktop_config.json:
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.