MCP server for working with STAC (SpatioTemporal Asset Catalog) API for searching and accessing geospatial data. Enables AI assistants to search satellite imagery, metadata, and other geospatial datasets.

Installation

UVX

uvx --from git+https://github.com/wayfinder-foundry/stac-mcp stac-mcp

Docker

docker run --rm -i ghcr.io/wayfinder-foundry/stac-mcp:latest

Podman

podman run --rm -i ghcr.io/wayfinder-foundry/stac-mcp:latest

From Source Code

git clone https://github.com/wayfinder-foundry/stac-mcp.git
cd stac-mcp
pip install -e ".[dev]"

Configuration

MCP Server Configuration

{
  "stac": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/wayfinder-foundry/stac-mcp",
      "stac-mcp"
    ],
    "transport": "stdio",
  }
}

Available Tools

Tool	Description
get_root	Get the root document (subset of id/title/description/links/conformance)
get_conformance	Get a list of all conformance classes; optionally check specific URIs
search_collections	Get a list and search available STAC collections
get_collection	Get detailed information about a specific collection
search_items	Search STAC items with spatial, temporal, and attribute filters
get_item	Get detailed information about a specific STAC item
estimate_data_size	Estimate data size for STAC items using lazy loading (XArray + odc.stac)
get_queryables	Returns properties available for querying in STAC search
get_aggregations	Creates STAC Search requests with aggregation for data analysis

Capabilities

• Search and browse STAC collections
• Search geospatial datasets (satellite imagery, metadata, etc.)
• Access metadata and asset information
• Perform spatial and temporal queries
• Dual output mode (text and structured JSON) for all tools
• Estimate data size with lazy loading without downloading
• Crop areas of interest for accurate size estimation
• Capability discovery and graceful fallbacks
• Support for batch processing with structured metadata

Usage Examples

Find Landsat satellite imagery in the San Francisco Bay Area for January 2023

Get detailed information about a specific STAC collection

Estimate the data size of satellite imagery without downloading it

Find weather metadata collections available in the STAC catalog

Search geospatial elements with specific temporal and spatial filters

Notes

The server supports dual output mode with an optional 'output_format' parameter ('text' by default or 'json'). JSON mode returns structured data wrapped in MCP TextContent. The server includes complete FastMCP documentation and architectural recommendations for agentic geospatial analysis.