mcp · Global

GEO_INFER

GEO-INFER — a 44-module geospatial inference monorepo from the Active Inference Institute. Spatial analysis, active inference, domain modeling, agent workflows, and reproducible repository validation in one uv/Python workspace (H3, Bayesian models, place & risk).

Visit source ↗GitHub repository ↗

Feature or claim this listing

Feature this listing — founding Featured slots are 50% off for 6 months

Represent GEO_INFER? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: H3 cell indexing: WGS84 lat/lng to H3 cell and back (latlng_to_cell, cell_to_latlng) · Bayesian models · Active Inference agents with beliefs, actions and free-energy terms · Earth-system domain modules (water, marine, forest, climate, energy, transport, emergency)
Resolution docs-verified: H3 grid cells; resolution is an integer parameter (example resolution=9); no metric cell size documented
Formats docs-verified: Python library (uv workspace packages, Python 3.11+) · CLI (geo-infer) · MCP (transport not documented) · agent skills
Access docs-verified: Source repository on GitHub; no auth documented. Licence CC BY-NC-SA 4.0 per docs (non-commercial, share-alike); ENTRY lists 'Other'.

Useful for

Use cases llm-inferred: Index site, gauge and survey-point locations to H3 cells for consistent spatial binning across a study area · Prototype Bayesian uncertainty models for screening-level spatial risk, with research-grade validation · Run the repo's own test and contract scripts before adapting the spatial modules into an in-house pipeline
Audience llm-inferred: GIS analysts · hydrologists (research use) · Python developers · spatial data scientists

Limitations

Constraints docs-verified: Code library and developer workspace, not a data API: no real-world datasets (river levels, rainfall, DEM, flow) are documented · Packages are under active development; outstanding acceptance requirements are tracked separately · Coordinates are WGS84 lat/lng; no British National Grid (OSGB) handling is documented · Licence CC BY-NC-SA 4.0 is non-commercial per docs, while ENTRY says 'Other'; check before commercial consultancy use · Needs a local Python 3.11+ uv install; no hosted endpoint, auth or MCP transport documented · ENTRY 'tools' are repo validation scripts, not documented geospatial MCP tools; ENTRY says 44 modules, docs say 45 · GEO-INFER-WATER is named, but its functions and data are not described in these docs

Licence: Other
Authentication: Unknown — review source docs
GitHub stars: 18
Last commit: 18/10/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, auth. Check upstream documentation.

Provenance & evidence

Daily discovery 2026-10-18: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · daily-2026-10-18 (github-search)