Durable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.
Web & Searchv1.5.1streamable-httpwingmanprotocol.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 239ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo com.wingmanprotocol.agent/gateway@1.5.1 |
| tooling | 35 / 35 | tools/list OK: 271 tools e.g. "discover_tools"; 271/271 described, 269/271 fully-typed schemas, median description 137 chars |
| latency | 10 / 10 | initialize round-trip 239ms |
| provenance | 8 / 15 | description present; repository linked; version 1.5.1; namespace com.wingmanprotocol.agent does NOT match remote host (expected *.agent.wingmanprotocol.com) |
Score 93/100 · latency 239ms · 271 tools · auth: open
Claude Code:
claude mcp add --transport http gateway https://wingmanprotocol.com/mcp
Generic MCP client config:
{ "mcpServers": { "gateway": { "type": "http", "url": "https://wingmanprotocol.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/com.wingmanprotocol.agent/gateway · referral link https://mcpqueen.com/go/com.wingmanprotocol.agent/gateway (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.wingmanprotocol.agent/gateway)
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 09:30 | A | 93 | 239ms |