Argentina CUIT/CUIL validation and AFIP fiscal QR generation. Pure, no-auth MCP tools.
Dev & Codev1.0.0streamable-httptools.somosvelora.com
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 559ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo velora-mcp@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 9 tools e.g. "validate_cuit"; 9/9 described, 9/9 fully-typed schemas, median description 422 chars |
| latency | 7 / 10 | initialize round-trip 559ms |
| provenance | 5 / 15 | description present; no repository URL; version 1.0.0; namespace io.github.crossi-dev does NOT match remote host (expected *.crossi-dev.github.io) |
Score 87/100 · latency 559ms · 9 tools · auth: open
Claude Code:
claude mcp add --transport http latam-tools https://tools.somosvelora.com/api/mcp/public
Generic MCP client config:
{ "mcpServers": { "latam-tools": { "type": "http", "url": "https://tools.somosvelora.com/api/mcp/public" } } }
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.crossi-dev/latam-tools · referral link https://mcpqueen.com/go/io.github.crossi-dev/latam-tools (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.crossi-dev/latam-tools)
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 23:15 | B | 87 | 559ms |