Agent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.
AI & Agentsv2026.06.10streamable-httpjoinmultiplayer.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 711ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo multiplayer-remote@2026.06.10 |
| tooling | 35 / 35 | tools/list OK: 3 tools e.g. "ask_network"; 3/3 described, 3/3 fully-typed schemas, median description 151 chars |
| latency | 7 / 10 | initialize round-trip 711ms |
| provenance | 15 / 15 | description present; repository linked; version 2026.06.10; namespace ai.joinmultiplayer matches endpoint/repo |
Score 97/100 · latency 711ms · 3 tools · auth: open
Claude Code:
claude mcp add --transport http gpu https://joinmultiplayer.ai/mcp
Generic MCP client config:
{ "mcpServers": { "gpu": { "type": "http", "url": "https://joinmultiplayer.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.joinmultiplayer/gpu · referral link https://mcpqueen.com/go/ai.joinmultiplayer/gpu (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/ai.joinmultiplayer/gpu)
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 14:46 | A | 97 | 711ms |