cameronking4/google-earth-engine-mcp
If you are the rightful owner of google-earth-engine-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This document provides a comprehensive overview of the Google Earth Engine MCP Server, which utilizes the Vercel MCP Adapter to integrate MCP server capabilities into Next.js projects.
Google Earth Engine MCP Server
Uses @vercel/mcp-adapter
Usage
This sample app uses the Vercel MCP Adapter that allows you to drop in an MCP server on a group of routes in any Next.js project.
Update app/[transport]/route.ts
with your tools, prompts, and resources following the MCP TypeScript SDK documentation.
Google Earth Engine Tools
This project includes MCP tools for interacting with Google Earth Engine, a cloud-based platform for geospatial analysis. These tools allow AI assistants to:
- Initialize and authenticate with Earth Engine
- Visualize Earth Engine datasets as maps
- Retrieve information about Earth Engine datasets
- Compute statistics for Earth Engine data in specified regions
- Search for Earth Engine datasets
For more details, see the .
To use Earth Engine tools, you'll need:
- A Google Earth Engine account
- A Google Cloud service account with Earth Engine access
- A service account private key for authentication
Notes for running on Vercel
- To use the SSE transport, requires a Redis attached to the project under
process.env.REDIS_URL
- Make sure you have Fluid compute enabled for efficient execution
- After enabling Fluid compute, open
app/route.ts
and adjustmaxDuration
to 60 (or higher if using a Vercel Pro or Enterprise account) - Deploy the Next.js MCP template
Sample Client
script/test-client.mjs
contains a sample client to try invocations.
node scripts/test-client.mjs https://mcp-for-next-js.vercel.app