v0.0.2

Highlights

• Pluggable LLM provider layer (gee_mcp.server.llm): Google (Gemini Developer / Vertex AI), Anthropic, and OpenAI behind a common BaseLLM interface.
• New @register_llm decorator + from_env classmethod per provider — adding a provider is one decorated subclass.
• Optional on-disk response cache (JSONFileCache) injected via ResponseCache protocol; default is NullCache.
• Reasoning passthrough where supported (Anthropic adaptive thinking, OpenAI reasoning summaries).
• New test module tests/test_server/test_llm.py (24 tests, no network).

Breaking changes

• gee_mcp.server.genai module removed. Import from gee_mcp.server.llm instead (init_llm_client, BaseLLM, OpenAILLM, AnthropicLLM, GoogleLLM, …).
• LLM_PROVIDER (google | anthropic | openai) and LLM_NAME env vars are now required for the analysis / code-generation / coderun tools. Previously these defaulted implicitly to Gemini.
• Provider-specific credentials must match LLM_PROVIDER: OPENAI_API_KEY, ANTHROPIC_API_KEY, or one of GEMINI_API_KEY / GOOGLE_API_KEY / VERTEXAI_PROJECT.

See updated .env.example and README.md for configuration.

v0.0.1 - First public release

First public release of gee-mcp, an MCP server exposing Google Earth
Engine as MCP tools.

Highlights

• 23 MCP tools covering catalogue browsing, metadata extraction,
  analysis primitives (NDVI, zonal stats, threshold area, temporal
  composites, multi-period analysis, etc.), arbitrary GEE Python
  execution, and Gemini-driven code generation, factuality review,
  and sensitivity analysis.
• Single-call GEE auth: ee.Initialize delegates to the standard
  Google Cloud credential chain (GOOGLE_APPLICATION_CREDENTIALS,
  gcloud auth application-default login, the earthengine authenticate cache, GCE / Cloud Run instance metadata).
• Poetry packaging for Python 3.11 - 3.14, MIT licensed.
• Pre-commit suite: detect-secrets, autoflake, black, isort, mypy,
  pylint, pytest with coverage.
• CI on every push, running the full pre-commit suite across the
  Python matrix.

Getting started

git clone https://github.com/FrontierDevelopmentLab/gee-mcp.git
cd gee-mcp
poetry install
cp .env.example .env  # then fill in GEE_PROJECT and GEMINI_API_KEY
poetry run python -m gee_mcp.server

See README.md
for the full tool list, configuration reference, and integration
examples.