Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
AI & Agentsv0.3.3streamable-httppackagesmcp-perception-production.up.railway.app repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 374ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo geiant-perception@0.3.0 |
| tooling | 35 / 35 | tools/list OK: 8 tools e.g. "perception_fetch_tile"; 8/8 described, 8/8 fully-typed schemas, median description 200 chars |
| latency | 10 / 10 | initialize round-trip 374ms |
| provenance | 8 / 15 | description present; repository linked; version 0.3.3; namespace com.geiant does NOT match remote host (expected *.geiant.com) |
Score 93/100 · latency 374ms · 8 tools · auth: open
Claude Code:
claude mcp add --transport http mcp-perception https://packagesmcp-perception-production.up.railway.app/mcp
Generic MCP client config:
{ "mcpServers": { "mcp-perception": { "type": "http", "url": "https://packagesmcp-perception-production.up.railway.app/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.geiant/mcp-perception · referral link https://mcpqueen.com/go/com.geiant/mcp-perception (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.geiant/mcp-perception)
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 02:00 | A | 93 | 374ms |