Skip to main content
Glama

geo-evidence-mcp

An MCP server and agent for Earth-observation questions where every numeric answer ships with machine-checkable provenance: STAC item, collection, band, CRS, acquisition time, processing level and a replayable tool-call trace.

Status: M0 scaffold. Nothing below the status table is implemented yet.

Milestone

Scope

State

M0

Scaffold, compose, CI skeleton, ADR-001

in progress

M1

Data layer (search_stac, load_window, zonal_stats)

pending

M2

FastMCP server

pending

M3

Provenance schema + persistence + claim validator

pending

M4

LangGraph agent + Langfuse tracing

pending

M5

Refusal / low-confidence logic

pending

M6

Benchmark + eval runner

pending

M7

Naive vs provenance comparison

pending

M8

Polish, demo, v0.1.0

pending

Quickstart (M0)

make install        # uv sync
make init           # creates .env with generated secrets
make check          # ruff, mypy --strict, pytest
make up             # PostGIS + pgvector
make up-obs         # + self-hosted Langfuse (http://localhost:3000)

Benchmark results: PENDING (no real run exists yet).

License: MIT.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Turns the AWS Registry of Open Data and public STAC catalogs into agent-callable tools for dataset search, STAC queries, and NDVI/NDBI/land-cover analysis on Sentinel-2 imagery.
      -
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to autonomously discover, stream, and compute satellite analytics from free government Earth-observation catalogs such as Sentinel-2, Landsat, and Copernicus DEM, with zero API keys or configuration. It supports place-name geocoding, STAC scene search, cloud-native COG streaming for spectral indices, elevation profiles, SAR flood detection, and sandboxed custom geospatial scripts.
      29
      16
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to autonomously discover, stream, and compute satellite analytics from free government Earth observation archives. Provides tools for STAC search, spectral indices, elevation profiles, SAR water detection, and sandboxed geospatial scripting.
      29
      Apache 2.0