← Directory
mcp · Global
snap-rag-mcp-explore
AI-generated fever dream + demo: RAG over SNAP's GeoNetwork catalog plus an MCP server for live Alaska climate data (earthmaps.io), with attribution.
Claim this listing
Represent snap-rag-mcp-explore? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- temperature and precipitation · climate indicators · degree days · permafrost · snowfall · wet days · elevation · fire weather · flammability · vegetation · spruce beetle risk · hydrology · monthly CMIP6 · downscaled-daily CMIP6 · ERA5-WRF reanalysis · temperature anomalies · sea ice · landfast ice · current wildfire conditions · landslide monitoring · community demographics · stream hydrology
- Coverage docs-verified
- Alaska
- Formats llm-inferred
- MCP stdio
- Access docs-verified
- No API key or auth (auth null in metadata); find_place and get_climate_data work without extra setup; server runs locally from a Python environment; code MIT; data CC BY 4.0 unless a source provider specifies otherwise
Useful for
- Use cases llm-inferred
- Projected temperature and precipitation context for an Alaska site or community climate statement, using get_climate_data · Permafrost thaw screening for foundation or civils design near an Alaska community · Fire weather and fire danger baseline for an Alaska wildfire risk or site assessment · Pulling dataset methods, limitations and DOIs for an Alaska climate report via get_dataset
- Audience llm-inferred
- climate consultants · geotechnical engineers · civils engineers · hydrologists · environmental consultants · planners
Limitations
- Constraints docs-verified
- Alaska only: places are restricted to Alaska, CONUS hydrology is not offered, and there is no UK coverage · Self-described as an AI-generated personal experiment, not a supported product, and not reviewed for production use · search_datasets and get_dataset need a Lane 1 index built with harvest · Some topics need options such as variables, scenario, start_year/end_year or operation, and wrong options return errors · Responses can be large (hydrology without variables is 147 KB), so long series are summarised · Setup needs a mamba/conda environment and absolute paths in the MCP client config; first Lane 1 run downloads a ~80 MB model
- Licence
- MIT
- Authentication
- Unknown — review source docs
- GitHub stars
- 1
- Last commit
- 30/09/2026
- Last successful page check
- 14/10/2026
- Page health
- healthy
- Package
- Not recorded
- Verification
- Not independently verified
Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.
Provenance & evidence
Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.
Metadata observed 14/10/2026 · daily-2026-10-15 (github-search)