Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.
Dev & Codev1.3.0streamable-httpwww.agentcrush.xyz repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 247ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo AgentCrush@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 14 tools e.g. "search_agents"; 14/14 described, 14/14 fully-typed schemas, median description 235 chars |
| latency | 10 / 10 | initialize round-trip 247ms |
| provenance | 15 / 15 | description present; repository linked; version 1.3.0; namespace io.github.kristof-sudo matches endpoint/repo |
Score 100/100 · latency 247ms · 14 tools · auth: open
Claude Code:
claude mcp add --transport http agentcrush-app https://www.agentcrush.xyz/api/mcp/v1
Generic MCP client config:
{ "mcpServers": { "agentcrush-app": { "type": "http", "url": "https://www.agentcrush.xyz/api/mcp/v1" } } }
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.kristof-sudo/agentcrush-app · referral link https://mcpqueen.com/go/io.github.kristof-sudo/agentcrush-app (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.kristof-sudo/agentcrush-app)
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 |
|---|---|---|---|
| 2026-07-14 04:00 | A | 100 | 247ms |