Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Predictive Market Find arbitrage opportunities in crypto markets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that aggregates prediction market data from 5 major platforms. Search markets, compare odds, detect arbitrage opportunities, and track predictions through natural language.
Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.
Part of the Claude Code Plugin Marketplace.
Related MCP server: SimpleFunctions
# Clone and install
git clone https://github.com/EricGrill/mcp-predictive-market.git
cd mcp-predictive-market
uv sync
# Run the server
uv run python -m mcp_predictive_market.serverAdd to your Claude config and start querying markets:
"Find prediction markets about AI regulation"
Feature | Description |
Multi-Platform Search | Query 5 prediction markets simultaneously |
Arbitrage Detection | Find price discrepancies across platforms |
Market Tracking | Build watchlists and monitor odds changes |
Platform Comparison | Side-by-side odds for similar questions |
Unified Data Model | Consistent market schema across all platforms |
Tool | Description |
| Search markets across all platforms by keyword |
| Get available market categories |
| Browse markets in a specific category |
Tool | Description |
| Get current odds for a specific market |
| Side-by-side comparison of similar markets |
Tool | Description |
| Add a market to your watchlist |
| View all tracked markets with current prices |
Tool | Description |
| Detect price discrepancies between platforms |
Platform | URL | Specialization |
Manifold Markets | Play money, wide variety | |
Polymarket | Crypto, high liquidity | |
Metaculus | Science, long-term forecasts | |
PredictIt | US politics | |
Kalshi | CFTC-regulated, real money |
Add to your Claude Desktop config:
Platform | Config Path |
macOS |
|
Windows |
|
Linux |
|
{
"mcpServers": {
"prediction-market": {
"command": "uv",
"args": ["run", "--directory", "/path/to/mcp-predictive-market", "python", "-m", "mcp_predictive_market.server"]
}
}
}Add to your project .mcp.json or ~/.config/claude-code/mcp.json:
{
"mcpServers": {
"prediction-market": {
"command": "uv",
"args": ["run", "--directory", "/path/to/mcp-predictive-market", "python", "-m", "mcp_predictive_market.server"]
}
}
}"Find prediction markets about AI"
"What categories of markets are available?"
"Show me crypto markets on Polymarket"
"Browse politics markets""Get current odds for Manifold market abc123"
"Compare odds for 'Will Bitcoin hit $100k?' across all platforms"
"Show me the probability of a 2024 recession on different platforms""Find arbitrage opportunities with at least 10% spread"
"Are there any markets with significantly different odds across platforms?"
"Show me the biggest price discrepancies right now""Track the Polymarket election market"
"Show all my tracked markets"
"What are the current prices on my watchlist?"# Clone
git clone https://github.com/EricGrill/mcp-predictive-market.git
cd mcp-predictive-market
# Install with dev dependencies
uv sync --extra dev
# Run tests
uv run pytest -v
# Run specific test file
uv run pytest tests/test_integration.py -vsrc/mcp_predictive_market/
├── server.py # MCP server entry point
├── tools.py # Tool handler implementations
├── schema.py # Unified market data models
├── errors.py # Custom exceptions
├── rate_limiter.py # Per-platform rate limiting
├── adapters/ # Platform-specific adapters
│ ├── base.py # Adapter protocol
│ ├── manifold.py
│ ├── polymarket.py
│ ├── metaculus.py
│ ├── predictit.py
│ └── kalshi.py
├── analysis/ # Market analysis modules
│ ├── matching.py # Cross-platform market matching
│ └── arbitrage.py # Arbitrage detection
└── state/ # State management
└── memvid_client.pyPlatform API may be rate-limited - wait and retry
Check platform is online: visit the website directly
Some platforms filter certain market types
Lower the min_spread parameter (default is 5%)
Try broader search terms
Fewer opportunities exist in efficient markets
Verify the market ID format (varies by platform)
Ensure the market hasn't been resolved/closed
Check you're using the correct platform name
Claude Code Plugin Marketplace - Discover more MCP plugins
MCP Proxmox Admin - Manage Proxmox VE through Claude
MCP Memvid State Service - Persistent state for MCP servers
Contributions welcome!
Fork the repository
Create feature branch: git checkout -b feature/my-feature
Make changes and test: uv run pytest
Commit: git commit -m 'Add my feature'
Push: git push origin feature/my-feature
Open a Pull Request
MIT
Browse markets in a specific category
Inputs: category (required), limit.
Side-by-side odds comparison for markets matching a query
Inputs: query (required).
Find price discrepancies across platforms
Inputs: min_spread.
Get current odds for a specific market
Inputs: platform (required), market_id (required).
Get all markets in your watchlist with current prices
Inputs: no named parameters.
List available market categories
Inputs: no named parameters.
Search for prediction markets across platforms
Inputs: query (required), platforms.
Add a market to your tracking watchlist
Inputs: platform (required), market_id (required), alias.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 8 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, 'browse_category' focuses on category-specific browsing, 'search_markets' handles cross-platform search, and 'get_market_odds' retrieves specific market data, ensuring agents can easily differentiate between them.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'browse_category', 'compare_platforms', and 'track_market'. This uniformity makes the tool set predictable and easy to navigate for agents.
With 8 tools, the server is well-scoped for predictive market analysis, covering key operations like browsing, searching, comparing, and tracking. Each tool earns its place without feeling excessive or insufficient for the domain.
The tool set provides strong coverage for core workflows, including market discovery, comparison, and tracking. A minor gap exists in direct market interaction tools, such as placing bets or managing user accounts, but agents can still perform essential analysis tasks effectively.
Cross-venue prediction market odds (Polymarket, Kalshi, PredictIt, Manifold) with arbitrage signals
Polymarket & Kalshi live prediction market odds aggregator and cross-venue arbitrage scanner MCP.
Polymarket, Kalshi + 6 more prediction markets: live odds, volume, movers. Read-only, no auth.
Live Kalshi + Polymarket prediction-market data and cross-venue arbitrage spreads, one schema.