Mcp Perception

gns-foundation/geiant

Brings satellite imagery, weather data, and geospatial foundation models (IBM Prithvi, Microsoft Clay) into Claude through MCP. Every operation is scoped to H3 hexagon cells and runs through geometry validation via GEOS to catch self-intersections and malformed polygons before they hit your workflow. Built on the GNS Protocol, so each request carries cryptographic proof of jurisdiction and regulatory context (GDPR, EU AI Act, CCPA). The stack connects to GDAL, PostGIS, ArcGIS, and QGIS under the hood. Reach for this when you need Claude to reason over real geography with compliance guardrails baked in, not bolted on.

tools: 8
transport: HTTP
last updated: Apr 11, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://packagesmcp-perception-production.up.railway.app/mcp --name mcp-perception

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http mcp-perception https://packagesmcp-perception-production.up.railway.app/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 8 tools

Verified live against the running server on Nov 6, 2026.

perception_fetch_tileFetch the least-cloudy Sentinel-2 L2A tile covering a given H3 cell from Microsoft Planetary Computer. Returns signed COG band URLs for all 6 Prithvi/Clay spectral bands (B02 Blue, B03 Green, B04 Red, B8A NIR, B11 SWIR1, B12 SWIR2), plus tile metadata. The tile is cached in me...4 params

Fetch the least-cloudy Sentinel-2 L2A tile covering a given H3 cell from Microsoft Planetary Computer. Returns signed COG band URLs for all 6 Prithvi/Clay spectral bands (B02 Blue, B03 Green, B04 Red, B8A NIR, B11 SWIR1, B12 SWIR2), plus tile metadata. The tile is cached in me...

Parameters* required

days_backnumber

Days to search back. Default: 30.

h3_cell*string

H3 cell ID at any resolution.

max_cloud_covernumber

Max cloud cover %. Default: 20.

timestampstring

ISO 8601 datetime. Search back from this point. Defaults to now.

perception_classifyRun Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-band chip to a RunPod endpoint and returns: dominant_class, flood_pixel_pct, confidence, class_counts, and the full perception_chain. The...4 params

Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-band chip to a RunPod endpoint and returns: dominant_class, flood_pixel_pct, confidence, class_counts, and the full perception_chain. The...

Parameters* required

h3_cellstring

Override H3 cell. Defaults to the cell from the original fetch.

task*string

Classification task. Currently only "flood" is supported.one of flood · landcover · burnscar · anomaly

tile_id*string

tile_id from perception_fetch_tile result (must be in session cache).

write_to_spatial_memoryboolean

Write perception chain to geiant_geometry_state. Default: true.

perception_embed[Sub-phase 4.2 — NOT YET IMPLEMENTED] Will generate Clay v1.5 embeddings.1 params

[Sub-phase 4.2 — NOT YET IMPLEMENTED] Will generate Clay v1.5 embeddings.

Parameters* required

tile_id*string

tile_id from perception_fetch_tile result

perception_weatherQuery atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Spatial Memory and drops a signed audit breadcrumb.3 params

Query atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Spatial Memory and drops a signed audit breadcrumb.

Parameters* required

h3_cell*string

H3 cell ID at any resolution.

timestampstring

ISO 8601 datetime for weather lookup. Defaults to now.

write_to_spatial_memoryboolean

Write weather context to geiant_geometry_state. Default: true.

gns_get_trust_scoreGet the current TierGate trust tier and score for an agent. Tiers: provisioned (0%) → observed (25%) → trusted (60%) → certified (85%) → sovereign (99%). Omit agent_pk to query the server's own agent.1 params

Get the current TierGate trust tier and score for an agent. Tiers: provisioned (0%) → observed (25%) → trusted (60%) → certified (85%) → sovereign (99%). Omit agent_pk to query the server's own agent.

Parameters* required

agent_pkstring

Ed25519 public key (64 hex chars). Omit for own agent.

gns_verify_chainVerify the cryptographic integrity of an agent's breadcrumb chain. Returns { is_valid, block_count, issues[] } plus epoch Merkle roots. A valid chain proves no audit records have been tampered with.1 params

Verify the cryptographic integrity of an agent's breadcrumb chain. Returns { is_valid, block_count, issues[] } plus epoch Merkle roots. A valid chain proves no audit records have been tampered with.

Parameters* required

agent_pkstring

Ed25519 public key (64 hex chars). Omit for own agent.

gns_roll_epochRoll all pending breadcrumbs into a new sealed epoch with a Merkle root. Returns { epoch_index, merkle_root, block_count, epoch_hash }. Call this at the end of a session to produce a tamper-evident compliance snapshot.

Roll all pending breadcrumbs into a new sealed epoch with a Merkle root. Returns { epoch_index, merkle_root, block_count, epoch_hash }. Call this at the end of a session to produce a tamper-evident compliance snapshot.

No parameters. Call it with no arguments.

gns_get_compliance_reportReturns a full EU AI Act compliance report for a GNS agent, including trust score, chain verification, Merkle epoch proofs, delegation certificate, and regulatory status.1 params

Returns a full EU AI Act compliance report for a GNS agent, including trust score, chain verification, Merkle epoch proofs, delegation certificate, and regulatory status.

Parameters* required

agentHandlestring

GNS handle of the agent (e.g. energy@italy-geiant)

Readme

🐜 GEIANT

Geo-Identity Agent Navigation & Tasking

The first AI orchestrator that knows where it is.

What is GEIANT?

GEIANT is a geospatial AI agent orchestration runtime built on the GNS Protocol. It is a direct competitor to LangChain, CrewAI, and AutoGen — with one structural difference: every agent has a cryptographic identity bound to an H3 territory, and every task is routed through a compliance enforcement layer before dispatch.

LangChain doesn't know where it is. GEIANT does.

The Ant Metaphor

In GEIANT, agents are ants. Ants are the canonical model of emergent collective intelligence from simple agents following spatial rules. Ant Colony Optimization (ACO) is a real algorithm used in routing and pathfinding. The colony is the orchestrated workflow. The territory is the H3 grid.

View the full README on GitHub

Details

Repository: github.com/gns-foundation/geiant
Transport: HTTP
Registry: MCP registry, active
Resources: 1
Tools verified: Nov 6, 2026

Mcp Perception

Install

Tools

Readme

🐜 GEIANT

What is GEIANT?

The Ant Metaphor

Details

More from gns-foundation