polymarket-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NAXOS_API_KEY | No | Optional NaxosData API key. When omitted, the server operates in public fallback mode. For live sub-second orderbooks and historical archives, provide a key from naxosdata.com. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_market_orderbookB | Retrieve normalized Level 2 orderbook depth for Polymarket, Kalshi, Limitless, PredictIt, ForecastEx, and more. Returns top bids, asks, best bid/ask, mid price, spread in basis points (bps), and orderbook imbalance (OBI). |
| scan_arbitrage_opportunitiesA | Find cross-venue matched prediction market arbitrage opportunities (e.g., Polymarket YES vs Kalshi NO, PredictIt vs Polymarket). Calculates exact net ROI, gross edge cents, combined costs, annualized yield, and oracle risk. |
| calculate_kalshi_feesB | Solve exact quadratic taker fees and maximum counterpart contract prices for Kalshi. Implements CFTC Rule 40.2 quadratic fee formula: ceil(0.07 * C * P * (1-P)), and solves the closed-form quadratic root solver 0.07P_no^2 - 1.07P_no + K >= 0 for guaranteed positive EV cross-venue arbitrage. |
| get_whale_tradesB | Query recent block trades and institutional whale orderflow with on-chain wallet addresses, trade sizes, prices, and transaction hashes across Polymarket, Kalshi, and Limitless. |
| search_prediction_marketsA | Search active prediction markets across 7 major venues (Polymarket, Kalshi, Limitless, PredictIt, Drift BET, Smarkets, ForecastEx). Filter by keyword, category, status, or specific venue to view live quotes, volume, and liquidity. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct action-object pair: orderbook depth, arbitrage scanning, market search, fee math, and whale flow. While orderbook and arbitrage both touch pricing data, the descriptions make the boundaries explicit (raw depth vs. cross-venue opportunity detection). No realistic misselection risk.
All five tools follow a strict verb_noun snake_case convention: get_market_orderbook, search_prediction_markets, scan_arbitrage_opportunities, calculate_kalshi_fees, get_whale_trades. Verbs are precise and non-redundant across the set.
Five tools is a tight, well-scoped set for a multi-venue prediction-market analytics server, with no filler. It is slightly thin relative to the breadth claimed (7 venues), leaving no room for market detail lookup or historical data tools, but nothing extraneous exists.
The surface covers the core analytical loop: discover markets, inspect depth/pricing, find cross-venue arbitrage, compute venue-specific fees, and track whale flow. Minor gaps remain—no single-market detail-by-id lookup, historical price series, or venue enumeration—which agents can partly work around via search_prediction_markets.