Fuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.
Otherv4.0.0streamable-httpmcp.nefesh.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 589ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo nefesh@1.26.0 |
| tooling | 35 / 35 | tools/list OK: 6 tools e.g. "get_human_state"; 6/6 described, 6/6 fully-typed schemas, median description 761 chars |
| latency | 7 / 10 | initialize round-trip 589ms |
| provenance | 15 / 15 | description present; repository linked; version 4.0.0; namespace ai.nefesh matches endpoint/repo |
Score 97/100 · latency 589ms · 6 tools · auth: open
Claude Code:
claude mcp add --transport http human-state https://mcp.nefesh.ai/mcp
Generic MCP client config:
{ "mcpServers": { "human-state": { "type": "http", "url": "https://mcp.nefesh.ai/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/ai.nefesh/human-state · referral link https://mcpqueen.com/go/ai.nefesh/human-state (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/ai.nefesh/human-state)
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 |
|---|---|---|---|
| 2026-07-12 15:01 | A | 97 | 589ms |