Gmail Local MCP

Gmail Local MCP

Local stdio MCP server that mirrors the public Gmail MCP server tool surface while calling the Gmail REST API directly, enabling email management tasks like creating drafts, searching threads, and managing labels.

Category
Visit Server

README

Gmail Local MCP

Local stdio MCP server that mirrors the public Gmail MCP server tool surface while calling the Gmail REST API directly. It is intended as a temporary stand-in for https://gmailmcp.googleapis.com/mcp/v1.

Setup

  1. Follow Google's official Configure the Gmail MCP server guide to provision a Google Cloud project, enable the Gmail API and Gmail MCP API, configure the OAuth consent screen, and create a Google OAuth desktop client.
  2. Copy config.sample.json to config.json.
  3. Fill in oauth.clientId and oauth.clientSecret with the OAuth client values from the official provisioning flow, then set the official Gmail MCP scopes:
    • https://www.googleapis.com/auth/gmail.readonly
    • https://www.googleapis.com/auth/gmail.compose
  4. Run npm install and npm run build.

config.json and .gmail-token.json are gitignored. On startup the server refreshes saved tokens when possible. If no token is present, or the token cannot be refreshed, it starts a localhost OAuth callback and opens the Google login page in your browser.

OAuth redirect URI

The local OAuth callback URL is:

http://127.0.0.1:<redirectPort>/oauth2callback

If you use a Google OAuth Web application client, set redirectPort in config.json to a fixed port and add that exact URL to the client's Authorized redirect URIs. For example, with "redirectPort": 3000, add:

http://127.0.0.1:3000/oauth2callback

The default sample uses "redirectPort": 0, which lets the OS choose an available port. That is convenient for a Google OAuth Desktop app client, but it is not suitable for a Web application client because the redirect URI must be registered exactly.

Official remote Gmail MCP configuration

If you want to use Google's hosted Gmail MCP server instead of this local stdio stand-in, use the official server URL and OAuth configuration from Google's provisioning guide:

{
  "mcpServers": {
    "gmail": {
      "httpUrl": "https://gmailmcp.googleapis.com/mcp/v1",
      "oauth": {
        "enabled": true,
        "clientId": "OAUTH_CLIENT_ID",
        "clientSecret": "OAUTH_CLIENT_SECRET",
        "scopes": [
          "https://www.googleapis.com/auth/gmail.readonly",
          "https://www.googleapis.com/auth/gmail.compose"
        ]
      }
    }
  }
}

Replace OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET with the OAuth client values you created in Google Cloud.

MCP client configuration

Use stdio transport and point your client at the built server. Replace /path/to/gmail-local-mcp with the directory where you cloned or copied this repo.

GitHub Copilot CLI

Add this server to your Copilot CLI MCP server configuration:

{
  "mcpServers": {
    "gmail": {
      "command": "node",
      "args": [
        "/path/to/gmail-local-mcp/dist/src/index.js",
        "--config",
        "/path/to/gmail-local-mcp/config.json"
      ]
    }
  }
}

On Windows, use escaped backslashes in JSON paths, for example C:\\path\\to\\gmail-local-mcp\\dist\\src\\index.js.

For development, use npm run dev -- --config config.json.

Tools

The server exposes the same 10 tool names as the public Gmail MCP server:

create_draft, list_drafts, get_thread, search_threads, label_thread, unlabel_thread, list_labels, label_message, unlabel_message, and create_label.

Non-interactive testing

You can provide a short-lived access token without writing it to disk. In this mode, config.json is optional:

$env:GMAIL_ACCESS_TOKEN = "ya29..."
npm run e2e

The e2e script only calls read/list tools so it can run with the official Gmail MCP scope set.

License

This project is licensed under the MIT License.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured