mcpField
G
Gmail Mcp Client Server

Gmail Mcp Client Server

Local
github.com/karimdabbouzCommunication0Updated 85w ago

About Gmail Mcp Client Server

Gmail Mcp Client Server is a project for connecting Claude with Gmail through a client and server. The README documents browser-based Gmail OAuth authentication and saving the resulting session for later startup.

Key features

  1. 01Connect Claude with Gmail
  2. 02Authenticate through a browser
  3. 03Save the authenticated session

Use cases

  1. 01Authorize Gmail access with OAuth
  2. 02Reuse a saved Gmail session when starting the client and server

MCP support

The project describes an MCP client and server connection for Claude and Gmail; the README provides no further details about the MCP capabilities exposed.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Important: Authenticating with Gmail

Manual OAuth authentication via the browser is required to work with Gmail. To do so, run server.py once as a standalone script with the credentials.json file next to the server.py script. It will then ask you to authenticate using your browser. After authenticating, the session is saved as token.pickle in the root of this project. You can then use this pickle file to start the client and server via the client.py file.

Information on authentication with Gmail and getting the credentials.json file: https://developers.google.com/gmail/api/quickstart/python

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.