Skip to main content

Gods Eye — civilian open-source geospatial awareness MCP. Wraps open-licence APIs (ESA Copernicus Sentinel-1/2/3/5p, OpenStreetMap, Overture, Ordnance Survey UK, INSPIRE EU, DEFRA) behind the MEOK Care Membrane ethics gate. For AI-agent situational awareness, environmental compliance, disaster response, agriculture. Refuses targeting and personal-surveillance queries. By MEOK AI Labs.

Project description

Gods Eye — Open-Source Geospatial Awareness MCP

Civilian open-source geospatial awareness for AI agents, wrapping open-licence APIs behind the MEOK Care Membrane ethics gate.

By MEOK AI Labs.

What it does

  • Wraps ESA Copernicus Sentinel-1/2/3/5p (SAR, multispectral, ocean/land/thermal, atmospheric)
  • Wraps OpenStreetMap + Overture Maps + Ordnance Survey UK + INSPIRE EU + DEFRA UK
  • Every query passes through the Care Membrane — a pre-inference ethics gate that refuses targeting, personal tracking, and surveillance patterns
  • Provides data-provenance checks — flag proprietary / closed-licence dependencies in an existing stack and suggest open-licence, EU/UK-hosted alternatives for GDPR and data-residency mandates

Why open-licence

  • Civilian projects (environmental NGOs, municipalities, research groups, CSRD reporters, agriculture co-ops, disaster response agencies) increasingly need open-data + known data-residency for GDPR and cost predictability
  • Copernicus is free, EU-hosted, all-weather SAR + 13-band multispectral — you don't need Maxar or Planet to answer 80% of civilian questions
  • Care Membrane provides governance-auditable decisions before any external API call
  • Designed to complement our csrd-compliance-mcp, eu-ai-act-compliance-mcp, gdpr-compliance-mcp

What it is NOT

  • Not for targeting. Care Membrane refuses patterns like "strike package", "find-fix-finish", "target elimination", "bounty", "lethal" and similar.
  • Not a replacement for Maxar/Planet where sub-metre commercial imagery is genuinely required.
  • Not a face-recognition or individual-tracking tool. Any such query is blocked.

Install

pip install gods-eye-geospatial-mcp

Claude Desktop

{
  "mcpServers": {
    "gods-eye": { "command": "gods-eye-geospatial-mcp" }
  }
}

Use cases

  • AI agent situational awareness (location → weather, terrain, infrastructure)
  • Maritime domain awareness (aggregate shipping, non-individual vessels)
  • Agriculture / yield estimation (NDVI / NDWI time series)
  • Infrastructure change detection (before / after)
  • Disaster response (flood / wildfire / earthquake overlays)
  • Environmental compliance evidence (CSRD E3 water, E4 biodiversity)

Tiers

  • Free — 10 situational queries/day, data-provenance checks
  • Pro £199/mo — unlimited + auto-fetches tiles + caches + signed attestations
  • Enterprise £1,499/mo — multi-tenant, on-prem deployment option, custom Care Membrane policies
  • 48h audit £5,000 — open-data provenance review of your entire geospatial stack

Care Membrane

The Care Membrane is MEOK's pre-inference ethics gate. Every query is evaluated for high-risk patterns before an external API is called. Policy is visible via the care_membrane_policy tool and reviewable by auditors.

License

MIT — MEOK AI Labs, 2026.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gods_eye_geospatial_mcp-1.2.0.tar.gz (9.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gods_eye_geospatial_mcp-1.2.0-py3-none-any.whl (11.9 kB view details)

Uploaded Python 3

File details

Details for the file gods_eye_geospatial_mcp-1.2.0.tar.gz.

File metadata

  • Download URL: gods_eye_geospatial_mcp-1.2.0.tar.gz
  • Upload date:
  • Size: 9.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for gods_eye_geospatial_mcp-1.2.0.tar.gz
Algorithm Hash digest
SHA256 b7ca7e0688aeedb64d0d61713a1866c896e2743034556f44b307991ab4c703bb
MD5 930e32bce58f466f5fdd0a0e277e5fe7
BLAKE2b-256 e8477cfd04fb02e4bd61920a3584ccfd0f0bf45821991671244b17a8991d2ce3

See more details on using hashes here.

File details

Details for the file gods_eye_geospatial_mcp-1.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for gods_eye_geospatial_mcp-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4360296ee7ca8a4664f3c0183176b6c77e0fe1d701ae56c6d84dda8523af2c13
MD5 34a41e314c3a6a8a04af092c2aed6329
BLAKE2b-256 f0f614560afb0c394b8dd7b73a8e263356466ab14428dccaf74c5b7c146d447d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page