Exa · Prediction-market odds, price history, order books, holders
Polymarket
Polymarket data through the Exa Agent: current prediction markets and events with implied-probability prices, volume and liquidity; price history of an outcome; live order books; top holders and a trader's positions and recent activity. Ask in natural language and, for structured output, pass output_schema naming the fields you want from Polymarket. Examples: "Market-implied probability of a Fed rate cut at the next meeting, and how it moved over the past month." "Top five position holders of the most liquid market about the next US election." Price: Exa effort (minimal $0.012, low $0.025, medium $0.10, high $0.50 per run) plus Polymarket calls are free: only the Exa effort is charged; the cost Exa reports is billed, up to max_cost_usd (default $0.025). Usually answers inline within a minute; otherwise returns a run id to read with exa/agent-run-get.
Usage based ExaFinanceexa/polymarketListed
Activation pending; your agent will see it as unavailable until then.
Use this tool with your agent
Use my connected Agentik MCP server. I want to use the tool exa/polymarket (Polymarket via Exa: prediction-market odds, price history, order books, holders). Call inspect_tool with {"tool_id": "exa/polymarket"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "exa/polymarket" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.Show the prompt
Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | Yes | What you want from Polymarket, in natural language. Be explicit about the entities (domains, tickers, company names, routes, dates) and the fields you expect. |
output_schema | object | No | Optional JSON Schema for the structured answer (returned in output.structured). Name each field after the Polymarket data you want, e.g. {"type":"object","required":["domain","monthlyVisits"],"properties":{"domain":{"type":"string"},"monthlyVisits":{"type":"number","description":"from Polymarket"}}}. |
effort | string | No | Exa Agent effort: minimal $0.012 (one quick lookup), low $0.025 (default), medium $0.10, high $0.50, plus partner calls. Options: minimal, low, medium, high. |
max_cost_usd | number | No | Ceiling reserved for this run, effort plus Polymarket calls (default $0.025, at most $2). The real cost Exa reports is billed, never more than this. |
How your agent calls it
First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:
{
"tool_id": "exa/polymarket",
"input": {
"query": "The current Polymarket market-implied probability of a US recession this year, from the most liquid matching market.",
"effort": "minimal"
}
}Price and billing
- Price
- Usage based
- Model
- Usage based
- Detail
- Billed at the cost the provider reports for the call, never above $2. Your agent sees the maximum before running.
- The provider’s price, 0% markup.
- One prepaid balance for every provider; your agent sees the price before it runs.
- Pay for measured usage; unused reservations are released.