Polymarket + Hyperliquid + macro for AI agents. 38 tools, signal backtest, SSE streaming. Free tier.
Dev & Codev0.5.0streamable-httppredmcp.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1297ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo PredMCP@0.7.0 |
| tooling | 35 / 35 | tools/list OK: 47 tools e.g. "create_api_key"; 47/47 described, 47/47 fully-typed schemas, median description 195 chars |
| latency | 7 / 10 | initialize round-trip 1297ms |
| provenance | 15 / 15 | description present; repository linked; version 0.5.0; namespace io.github.RavioleLabs matches endpoint/repo |
Score 97/100 · latency 1297ms · 47 tools · auth: open
Claude Code:
claude mcp add --transport http predmcp https://predmcp.com/mcp
Generic MCP client config:
{ "mcpServers": { "predmcp": { "type": "http", "url": "https://predmcp.com/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/io.github.RavioleLabs/predmcp · referral link https://mcpqueen.com/go/io.github.RavioleLabs/predmcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.RavioleLabs/predmcp)
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 18:48 | A | 97 | 1297ms |