17-model LLM gateway + 350+ data/KYB/sanctions tools. Pay-per-call USDC via x402, no API key.
Dev & Codev2.1.0streamable-httpapi.gocreativeai.com
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 960ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo gocreative-agent-api@1.27.1 |
| tooling | 35 / 35 | tools/list OK: 546 tools e.g. "bundle_kyb_360"; 546/546 described, 546/546 fully-typed schemas, median description 163 chars |
| latency | 7 / 10 | initialize round-trip 960ms |
| provenance | 5 / 15 | description present; no repository URL; version 2.1.0; namespace io.github.ColinHughes2121 does NOT match remote host (expected *.colinhughes2121.github.io) |
Score 87/100 · latency 960ms · 546 tools · auth: open
Claude Code:
claude mcp add --transport http gocreative-agent-api https://api.gocreativeai.com/mcp
Generic MCP client config:
{ "mcpServers": { "gocreative-agent-api": { "type": "http", "url": "https://api.gocreativeai.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/io.github.ColinHughes2121/gocreative-agent-api · referral link https://mcpqueen.com/go/io.github.ColinHughes2121/gocreative-agent-api (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.ColinHughes2121/gocreative-agent-api)
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 14:46 | B | 87 | 960ms |