Brand audits, visual catalogs, AI proposals & checkout for LATAM SMBs. Full funnel via MCP.
Dev & Codev1.0.0streamable-httpapp.thefusion.studio repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 212ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo mcp-typescript server on vercel@0.1.0 |
| tooling | 35 / 35 | tools/list OK: 6 tools e.g. "brand_audit"; 6/6 described, 6/6 fully-typed schemas, median description 179 chars |
| latency | 10 / 10 | initialize round-trip 212ms |
| provenance | 8 / 15 | description present; repository linked; version 1.0.0; namespace io.github.leonsm does NOT match remote host (expected *.leonsm.github.io) |
Score 93/100 · latency 212ms · 6 tools · auth: open
Claude Code:
claude mcp add --transport http fusion-studio-branding https://app.thefusion.studio/api/mcp
Generic MCP client config:
{ "mcpServers": { "fusion-studio-branding": { "type": "http", "url": "https://app.thefusion.studio/api/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.leonsm/fusion-studio-branding · referral link https://mcpqueen.com/go/io.github.leonsm/fusion-studio-branding (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.leonsm/fusion-studio-branding)
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 |
|---|---|---|---|
| 2026-07-14 04:45 | A | 93 | 212ms |