Mantis
Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mantis": {
"url": "https://prediction-router-chi.vercel.app/mcp"
}
}
}Remote endpoints
https://prediction-router-chi.vercel.app/mcpstreamable-httphttps://mantiss.store/mcpstreamable-httpWhat it can do
Tool inventory
Tools (6)
🟢route_market(q)
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.
Input Schema
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Natural language question or trading intent, e.g. \"Will BTC reach $200k in 2025?\" or \"Fed rate cut September\""
}
},
"required": [
"q"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_arbitrage(min_spread_pct, include_fees, position_size, venue_a, venue_b)
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.
Input Schema
{
"type": "object",
"properties": {
"min_spread_pct": {
"default": 4,
"description": "Minimum spread in percentage points (default 4 = 4¢)",
"type": "number",
"minimum": 1,
"maximum": 50
},
"include_fees": {
"default": false,
"description": "Whether to include estimated fee/friction normalization",
"type": "boolean"
},
"position_size": {
"default": 0,
"description": "USD position size used for fee/slippage estimation",
"type": "number",
"exclusiveMinimum": 0
},
"venue_a": {
"description": "Optional venue filter for one side of the arbitrage pair, e.g. polymarket",
"type": "string"
},
"venue_b": {
"description": "Optional venue filter for the other side of the arbitrage pair, e.g. kalshi",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢execute_url(market_id, canonical_id, side, amount, source, ...)
Get a deep link URL to place a trade on the best venue for a given market. The URL has a referral code embedded so the platform earns commission. Call this to get the URL, then direct the user to open it.
Input Schema
{
"type": "object",
"properties": {
"market_id": {
"description": "Platform-specific market ID (e.g. \"polymarket-abc123\")",
"type": "string"
},
"canonical_id": {
"description": "Cross-venue canonical market ID",
"type": "string"
},
"side": {
"default": "unknown",
"description": "Which side to trade",
"type": "string",
"enum": [
"yes",
"no",
"unknown"
]
},
"amount": {
"description": "USD amount to trade (for tracking)",
"type": "number",
"exclusiveMinimum": 0
},
"source": {
"default": "direct",
"description": "Tool path that produced this execution intent",
"type": "string",
"enum": [
"direct",
"route",
"quote",
"arbitrage",
"webhook"
]
},
"route_query": {
"description": "Original route_market query when source is route",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_quote(market_id, canonical_id, size)
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.
Input Schema
{
"type": "object",
"properties": {
"market_id": {
"description": "Platform-specific market ID",
"type": "string"
},
"canonical_id": {
"description": "Cross-venue canonical market ID",
"type": "string"
},
"size": {
"default": 0,
"description": "USD size for YES-buy VWAP/slippage estimation",
"type": "number",
"exclusiveMinimum": 0
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_history(market_id, canonical_id, venue, from, to, ...)
Get historical OHLCV-style prediction market candles over a time range, including the latest stored depth snapshot within each bucket when available. Can also export CSV text or base64-encoded Parquet.
Input Schema
{
"type": "object",
"properties": {
"market_id": {
"description": "Platform-specific market ID",
"type": "string"
},
"canonical_id": {
"description": "Cross-venue canonical market ID",
"type": "string"
},
"venue": {
"description": "Venue filter, e.g. polymarket or kalshi",
"type": "string"
},
"from": {
"type": "string",
"description": "Inclusive ISO 8601 start timestamp"
},
"to": {
"type": "string",
"description": "Inclusive ISO 8601 end timestamp"
},
"granularity": {
"default": "1d",
"description": "Bucket size for history candles",
"type": "string",
"enum": [
"1m",
"5m",
"15m",
"1h",
"4h",
"1d"
]
},
"format": {
"default": "json",
"description": "Return JSON candles, CSV text payload, or base64-encoded Parquet payload",
"type": "string",
"enum": [
"json",
"csv",
"parquet"
]
}
},
"required": [
"from",
"to"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_unmet_demand(days, limit)
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.
Input Schema
{
"type": "object",
"properties": {
"days": {
"default": 7,
"description": "Lookback window in days (default 7)",
"type": "integer",
"minimum": 1,
"maximum": 90
},
"limit": {
"default": 20,
"description": "Max results (default 20)",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence