MCP Geocoder Rosetta

@richardschrammcom

Basic information

About MCP Geocoder Rosetta

A "rosetta stone" repo that shows creating simple geocoder MCP servers in python (with googlemaps sdk and direct googlemaps API with urllib) and typescript. CLI clients and documentation on adding them to Claude Desktop App.

MCP Geocoder Rosetta config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-geocoder-rosetta": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "mcp[cli]"
      ]
    }
  }
}

MCP Geocoder Rosetta tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Geocoder Rosetta?

A collection of Model Context Protocol (MCP) geocoder implementations in different languages and approaches, using the Google Maps API. It serves as a learning resource for developers building their own MCP tools.

How to use MCP Geocoder Rosetta?

Clone the repository, set the GOOGLE_MAPS_API_KEY environment variable, install the MCP CLI, and run one of the test scripts such as python run_geocoder.py <implementation>. The three implementations can be configured individually for integration with Claude Desktop via claude_desktop_config.json.

Key features of MCP Geocoder Rosetta

Three geocoder implementations (Python urllib, Python Google Maps SDK, TypeScript)
Minimal dependencies option using Python standard library
Supports integration with Claude Desktop via MCP
Includes debugging scripts and server/client separation modes
Warns against installing multiple implementations simultaneously

Use cases of MCP Geocoder Rosetta

Learning how to build MCP tools in multiple programming languages
Geocoding addresses via the Google Maps API through AI assistants
Comparing implementation approaches for dependencies, error handling, and code size
Debugging MCP client-server connectivity with provided test scripts
Setting up a geocoding tool for use in Claude Desktop

Frequently asked questions

What prerequisites are needed?

A Google Maps API key, Python 3.13+ (for Python implementations), Node.js 16+ (for TypeScript), and the MCP CLI tools.

How do I configure the Google Maps API key?

Set it as the `GOOGLE_MAPS_API_KEY` environment variable, or create a `.env` file in each implementation directory with that variable.

Can I run all three implementations at the same time?

No. The README strongly advises installing only one implementation at a time to avoid tool disambiguation issues in Claude Desktop.

What debugging resources are available?

The repository includes `debug_mcp.sh`, `test_direct.py`, `test_server.py`, and options to run the server and client separately for isolating connectivity issues.

How is the TypeScript implementation started?

The recommended method is to run `python run_geocoder.py typescript`, which automatically installs npm dependencies and starts the TypeScript server.

Comments

More Developer Tools MCP servers

Heard

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Hermoso

Hermoso is an AI marketing agent and AI ad generator you run from your AI agent: a remote MCP server that researches the ads already winning in your market, makes image and video ads and organic posts in your brand, publ

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP