mcp · Global

Talking-To-Air

An AI-powered environmental platform that enables natural language exploration of air quality data through agents, geospatial analysis, and interactive visualizations.

Visit source ↗GitHub repository ↗

Feature or claim this listing

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

Represent Talking-To-Air? 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: NASA satellite atmospheric data (built-in presets: OMI, TROPOMI, TEMPO NO2/O3/HCHO; any gridded NASA collection) · EPA ground-sensor air quality data via EPA AQS API · Trend plots · Vertical profiles for layered products · Statistical summaries over a region and date range · Dataset coverage and variable previews
Formats docs-verified: CSV · PNG · NetCDF
Access docs-verified: Requires credentials: Google AI Studio API key (GOOGLE_API_KEY), NASA Earthdata username and password, EPA AQS email and API key, and app-level sign-in via Supabase. Licence not stated.

Useful for

Use cases llm-inferred: Satellite NO2 column density trend over a site for an air-quality baseline (TROPOMI/TEMPO) · Comparing satellite NO2 against EPA ground monitors to check consistency for an assessment · Statistical summary of air quality over a project region and date range for planning or EIA context
Audience llm-inferred: environmental consultants · air quality specialists · GIS analysts · planners

Limitations

Constraints llm-inferred: Data sources are US-focused (NASA satellite presets and EPA AQS ground sensors); no UK coverage is stated in the docs · Satellite retrieval depends on the separate harmony-retrieval-mcp stack, which is optional · Retrieval size caps by default: 2 GiB soft, 10 GiB hard; larger requests pause for confirmation or are refused · Requires Docker Desktop, mkcert and local HTTPS setup; deployed as a web app (FastAPI, React, PostgreSQL), not documented as a standalone MCP server · No MCP tool names are documented, so the tool list in the entry is empty · Location lookups fail without a real contact email for the Nominatim geocoder

Licence: Unknown — check provider terms
Authentication: API key via env: AQS_API_KEY, CONNECTOR_ENCRYPTION_KEY, EARTHDATA_MCP_TOKEN, EARTHDATA_PASSWORD, EARTHDATA_USERNAME, GOOGLE_API_KEY (auto-extracted from README)
GitHub stars: 3
Last commit: 16/10/2026
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 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 16/10/2026 · daily-2026-10-15 (github-search)