io.github.Alfred768/mantis

Official6 tools

Mantis

Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals.

Routes prediction market trades across venues with arbitrage detection and quote history.

Captured live from the server via tools/list.

route_market

Find the best prediction market for a natural-language question or trading intent. Returns the best cross-venue match, current probability, liquidity, and any arbitrage opportunity between venues.

Parameters (1)

qstringrequired
Natural language question or trading intent, e.g. "Will BTC reach $200k in 2025?" or "Fed rate cut September"

get_arbitrage

Find live cross-venue arbitrage opportunities — markets where the same event trades at different prices on Polymarket vs Kalshi vs other venues. Can also estimate fee-normalized net spread for a position size.

Parameters (5)

min_spread_pctnumber
Minimum spread in percentage points (default 4 = 4¢)
include_feesboolean
Whether to include estimated fee/friction normalization
position_sizenumber
USD position size used for fee/slippage estimation
venue_astring
Optional venue filter for one side of the arbitrage pair, e.g. polymarket
venue_bstring
Optional venue filter for the other side of the arbitrage pair, e.g. kalshi

execute_url

Get a deep link URL to place a trade on the best venue for a given market. The URL has a referral code embedded so the platform earns commission. Call this to get the URL, then direct the user to open it.

Parameters (6)

market_idstring
Platform-specific market ID (e.g. "polymarket-abc123")
canonical_idstring
Cross-venue canonical market ID
sidestring
Which side to trade
amountnumber
USD amount to trade (for tracking)
sourcestring
Tool path that produced this execution intent
route_querystring
Original route_market query when source is route

get_quote

Get the live probability, liquidity, and volume for a prediction market across all venues. Can also return venue order book depth and size-aware VWAP/slippage estimates.

Parameters (3)

market_idstring
Platform-specific market ID
canonical_idstring
Cross-venue canonical market ID
sizenumber
USD size for YES-buy VWAP/slippage estimation

get_history

Get historical OHLCV-style prediction market candles over a time range, including the latest stored depth snapshot within each bucket when available. Can also export CSV text or base64-encoded Parquet.

Parameters (7)

market_idstring
Platform-specific market ID
canonical_idstring
Cross-venue canonical market ID
venuestring
Venue filter, e.g. polymarket or kalshi
fromstringrequired
Inclusive ISO 8601 start timestamp
tostringrequired
Inclusive ISO 8601 end timestamp
granularitystring
Bucket size for history candles
formatstring
Return JSON candles, CSV text payload, or base64-encoded Parquet payload

get_unmet_demand

Find questions that users are searching for but no prediction market exists. Useful for discovering new market creation opportunities or identifying emerging topics with real trading interest.

Parameters (2)

daysinteger
Lookback window in days (default 7)
limitinteger
Max results (default 20)

Install

claude_desktop_config.json

{
  "mcpServers": {
    "mantis": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mantiss.store/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.