Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
Remote server: your requests and data go to packagesmcp-perception-production.up.railway.app. Claude Code: claude mcp add --transport http mcp-perception https://packagesmcp-perception-production.up.railway.app/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
perception_fetch_tile — Fetch the least-cloudy Sentinel-2 L2A tile covering a given H3 cell from Microsoft Planetary Computer. Returns signed COG band URLs for all perception_classify — Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-bperception_embed — [Sub-phase 4.2 — NOT YET IMPLEMENTED] Will generate Clay v1.5 embeddings.perception_weather — Query atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Sgns_get_trust_score — Get the current TierGate trust tier and score for an agent. Tiers: provisioned (0%) → observed (25%) → trusted (60%) → certified (85%) → sovgns_verify_chain — Verify the cryptographic integrity of an agent's breadcrumb chain. Returns { is_valid, block_count, issues[] } plus epoch Merkle roots. A vagns_roll_epoch — Roll all pending breadcrumbs into a new sealed epoch with a Merkle root. Returns { epoch_index, merkle_root, block_count, epoch_hash }. Callgns_get_compliance_report — Returns a full EU AI Act compliance report for a GNS agent, including trust score, chain verification, Merkle epoch proofs, delegation certiNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.