Prediction-market quant tools for AI agents: EV, Kelly, arbitrage, edge for Kalshi & Polymarket.
AI & Agentsv1.2.0streamable-httppredictionmarketspicks.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 302ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo predictionmarketspicks@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 10 tools e.g. "calculate_ev"; 10/10 described, 10/10 fully-typed schemas, median description 359 chars |
| latency | 10 / 10 | initialize round-trip 302ms |
| provenance | 15 / 15 | description present; repository linked; version 1.2.0; namespace com.predictionmarketspicks matches endpoint/repo |
Score 100/100 · latency 302ms · 10 tools · auth: open
Claude Code:
claude mcp add --transport http quant https://predictionmarketspicks.com/api/mcp/mcp
Generic MCP client config:
{ "mcpServers": { "quant": { "type": "http", "url": "https://predictionmarketspicks.com/api/mcp/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/com.predictionmarketspicks/quant · referral link https://mcpqueen.com/go/com.predictionmarketspicks/quant (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.predictionmarketspicks/quant)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 05:45 | A | 100 | 302ms |