mcpField
G
Gmail MCP Server

Gmail MCP Server

Local
github.com/Himank-JCommunication0Updated 82w ago

About Gmail MCP Server

Gmail MCP Server connects Gmail functionality to LLMs through MCP. Its tools cover email actions such as sending messages, creating drafts, and marking messages as read; the project describes iterative prompting to use them without an agent framework.

Key features

  1. 01Send email
  2. 02Create drafts
  3. 03Mark email as read
  4. 04Use Gmail actions through LLM tool calls

Use cases

  1. 01Send an email requested in a prompt
  2. 02Prepare a draft message
  3. 03Mark a message as read

MCP support

The MCP server lists Gmail tools for an MCP client to invoke, and the README also describes a client that sends queries to the server.

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

Overview

Gmail MCP server - Connecting Gmail and LLM using MCP

Project

  • using functionalities of Gmail applications we create tools to send mail, create draft, mark email as read and more...
  • The aim is to to manually convert an LLM into an Agent without using any framework. Using iterative prompting we get our LLM to utilise tools and send email to required receipient

Demo

Watch how Gmail MCP server works

Code Details

MCP Server

This is the server file that enlists all the tools that our LLM can use. Below is the main code that opens FreeForm app, creates a rectangle and adds text inside it.

MCP Client

This is the client file that uses MCP to send the query to the server.

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.