Allow Claude to search and retrieve emails from your Gmail account.
credentials.json
in your project directoryRun the authorization command to generate your token:
uv run gmail-mcp auth --creds-path credentials.json --token-path token.json
This will open a browser window where you’ll need to log in to your Google account and grant the necessary permissions. After authorization, a token.json
file will be created in your project directory.
Add the Gmail MCP server to your Claude configuration file:
{
"mcpServers": {
"gmail": {
"args": [
"--from",
"git+https://github.com/vinayak-mehta/gmail-mcp",
"gmail-mcp"
],
"command": "/Users/username/.local/bin/uvx",
"env": {
"GMAIL_CREDS_PATH": "/Users/username/path/to/gmail-mcp/credentials.json",
"GMAIL_TOKEN_PATH": "/Users/username/path/to/gmail-mcp/token.json"
}
}
}
}
Make sure to:
/Users/username/path/to/gmail-mcp
with your actual project pathcommand
path to your installed uvx
executablecredentials.json
and token.json
filesClaude will now have access to the following tools:
Search for emails in your Gmail account.
Example prompt: “Search for all emails from [email protected]”
Retrieve the full content of a specific email.
Example prompt: “Show me the full content of the email with the subject ‘Meeting Tomorrow’”
List recent messages from your Gmail inbox.
Example prompt: “List my 5 most recent emails”
You can configure the paths to your credentials and token files using environment variables:
GMAIL_CREDS_PATH
: Path to your credentials.json fileGMAIL_TOKEN_PATH
: Path to your token.json fileCreate a .env
file in the project root with these variables for easy configuration.
A beginner-friendly guide server that helps users understand MCP concepts, provides interactive examples, and demonstrates best practices for building MCP integrations. Features tools for exploring MCP capabilities, resources for learning core concepts, and prompts for guided tutorials.
An MCP server that enables communication with users through Telegram. This server provides a tool to ask questions to users and receive their responses via a Telegram bot.
An MCP server that provides tools for retrieving and processing documentation through vector search, both locally or hosted. Enabling AI assistants to augment their responses with relevant documentation context.