google-maps-platform-code-assist-mcp
MCP server that retrieves up-to-date Google Maps Platform documentation and code samples to ground AI-generated code in official guidance.
README
[][npm-pkg]
[][license]
[
][Discord server]
Google Maps Platform Code Assist MCP toolkit (Alpha)
European Economic Area (EEA) developers If your billing address is in the European Economic Area, effective on 8 July 2025, the Google Maps Platform EEA Terms of Service will apply to your use of the Services. Functionality varies by region. Learn more.
Description
This repository contains code for a Model Context Protocol (MCP) server provides a tool (retrieve-google-maps-platform-docs) that retrieves context from fresh versions of Google Maps Platform documentation and code samples (including guides, API references, GitHub code sample repositories, and Terms of Service).
When used with an AI agent for coding assistance, this MCP server helps ground implementation plans and generated code in relevant, up-to-date, official Google Maps Platform guidance.
Requirements
- An MCP client, such as the MCP clients built into Gemini CLI, Gemini Code Assist, Cline, Roo Code, Claude Code, Cursor, Windsurf's Cascade, Firebase Studio and other AI coding assistants.
- A local machine on which to clone and run the MCP server that the MCP client can access.
- Node.js and npm (install) on the local machine.
Installation
Install for MCP clients that support npm installation
For any MCP client that supports installation via npm, use the command line to install the @googlemaps/code-assist-mcp MCP server to your local machine:
npx -y @googlemaps/code-assist-mcp
Install via JSON configuration (all other MCP clients)
Most MCP clients have a JSON file for their MCP configuration such as mcp.json (e.g. VSCode, Cursor) or mcp_config.json (Windsurf). Add the following to the MCP configuration file.
{
"mcpServers": {
"google-maps-platform-code-assist": {
"command": "npx",
"args": ["-y", "@googlemaps/code-assist-mcp"]
}
}
}
To deploy it in Gemini Code Assist follow these instructions.
MCP Tools and Resources
This toolkit provides tools and resources to ground AI-generated code in official, up-to-date Google Maps Platform guidance.
-
retrieve-google-maps-platform-docs(Tool): Submits a query to a hosted Retrieval Augmented Generation (RAG) engine that searches fresh versions of Google Maps Platform official documentation and code samples and returns relevant text or code to augment the context of generative AI responses. -
retrieve-instructions(Tool) /instructions(Resource): Used by the MCP client to get crucial system instructions and a preamble before callingretrieve-google-maps-platform-docs.
The intended use of these tools is to enrich the context of Generative AI models with the goal of reducing model hallucinations containing incorrect, irrelevant, inappropriate, or nonsensical content regarding Google Maps Platform. As your use of Google Maps Platform must comply with the Google Maps Platform Terms of Service, you should evaluate the performance of your model with the Google Maps Platform Code Assist toolkit against the Google Maps Platform documentation and the Google Maps Platform Terms of Service to verify compliance. To learn more about some best practices, see Responsible AI.
This tool sends information including the MCP client's query and IP address to a Google-hosted RAG service. Use of this service is subject to the Google Privacy Policy.
Contributing
Contributions are welcome. If you'd like to contribute, send us a pull request and refer to our code of conduct and contributing guide.
Terms of Service
This toolkit provides tools to describe the use of Google Maps Platform services. Use of Google Maps Platform services is subject to the Google Maps Platform Terms of Service, however, if your billing address is in the European Economic Area, the Google Maps Platform EEA Terms of Service will apply to your use of the Services. Functionality varies by region. Learn more.
This toolkit is not a Google Maps Platform Core Service. Therefore, the Google Maps Platform Terms of Service (e.g. Technical Support Services, Service Level Agreements, and Deprecation Policy) do not apply to the code in this repository or the RAG service called by it.
Support
This toolkit is offered via an open source license. It is not governed by the Google Maps Platform Support (Technical Support Services Guidelines, the SLA, or the Deprecation Policy). However, any Google Maps Platform services used by the library remain subject to the Google Maps Platform Terms of Service.
This library adheres to semantic versioning to indicate when backwards-incompatible changes are introduced. Accordingly, while the toolkit is in version 0.x, backwards-incompatible changes may be introduced at any time.
If you find a bug, or have a feature request, please file an issue on GitHub. If you would like to get answers to technical questions from other Google Maps Platform developers, ask through one of our developer community channels. If you'd like to contribute, please check the contributing guide.
You can also discuss this toolkit on our Discord server.
<!--repo-specific anchor links--> [npm-pkg]: https://npmjs.com/package/@googlemaps/code-assist-mcp
<!--constant anchor links--> [Discord server]: https://discord.gg/hYsWbmk [license]: LICENSE
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.