MCP QUEEN
app.humantaste/taste-mcp A
Expert review for AI agents. On-chain proof of human review.
AI & Agentsv2.0.0streamable-httpapi.humantaste.app repository
Grade evidence — probed 2026-07-12 18:48 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 775ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo taste-mcp@2.0.0 |
| tooling | 35 / 35 | tools/list OK: 20 tools e.g. "list_offerings"; 20/20 described, 20/20 fully-typed schemas, median description 400 chars |
| latency | 7 / 10 | initialize round-trip 775ms |
| provenance | 15 / 15 | description present; repository linked; version 2.0.0; namespace app.humantaste matches endpoint/repo |
Score 97/100 · latency 775ms · 20 tools · auth: open
Connect your agent
Claude Code:
claude mcp add --transport http taste-mcp https://api.humantaste.app/mcp/
Generic MCP client config:
{ "mcpServers": { "taste-mcp": { "type": "http", "url": "https://api.humantaste.app/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/app.humantaste/taste-mcp · referral link https://mcpqueen.com/go/app.humantaste/taste-mcp (counts as “routed via the queen”).
Own this server? Embed your grade badge
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/app.humantaste/taste-mcp)
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.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-12 18:48 | A | 97 | 775ms |