Skip to main content
Glama

STAC MCP Server

by BnJam
0001-baseline-mcp-stac-server.md1.05 kB
# ADR 0001: Baseline MCP STAC Server Status: Accepted Date: 2025-09-18 ## Context - Provide an MCP server that exposes common STAC workflows to AI assistants. - Use pystac-client for interoperability with STAC APIs (Planetary Computer by default). - Keep tests fast and offline via mocking. ## Decision - Implement a stdio MCP server with four tools: - search_collections, get_collection, search_items, get_item - Default catalog: https://planetarycomputer.microsoft.com/api/stac/v1 - Wrap pystac-client Client for API calls. - Text-first responses optimized for chat UX. - Logging via standard logging; graceful error logging for APIError. ## Consequences - Minimal, reliable baseline with broad catalog compatibility. - Does not yet expose all pystac-client features (filters, sorting, pagination, etc.). - Tests mock network; example script validates end-to-end behavior. ## Alternatives considered - Direct STAC API via requests (rejected: reinvents client features). - HTTP transport for MCP (rejected: stdio is the standard baseline).

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/BnJam/stac-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server