Gmail MCP Server Integration

What does “Gmail” MCP Server do?

The Gmail MCP Server is a Model Context Protocol (MCP) server designed to integrate Gmail functionalities into AI platforms such as Claude Desktop. Its primary role is to serve as a bridge between AI assistants and Gmail, allowing natural language interactions for managing emails. This includes sending and reading emails, managing labels, handling attachments, searching for specific messages, and performing batch operations. By exposing these capabilities as MCP tools and resources, the Gmail MCP Server enables developers to create powerful workflows where AI agents can automate and streamline email management, facilitate contextual data retrieval from inboxes, and manipulate Gmail content programmatically, all while leveraging secure OAuth2-based authentication.

List of Prompts

No explicit prompt templates are listed in the repository or documentation.

List of Resources

• Email Messages
  Exposes email messages as resources that can be read and used as context for LLM interactions.

• Gmail Labels
  Provides access to both system and user-defined Gmail labels, which can be used to organize or retrieve emails.

• Attachments Metadata
  Enables retrieval of information about email attachments, such as filenames, types, and sizes.

• Search Results
  Allows clients to access the results of advanced email searches based on subject, sender, or date range.

List of Tools

Based on the features listed in the documentation, the following tools are provided by the Gmail MCP Server:

• send_email
  Send emails with subject, content, attachments, and recipients, including support for HTML and international characters.

• read_email
  Retrieve email messages by ID, with support for complex MIME structures.

• list_labels
  List all available Gmail labels (system and user-defined).

• manage_labels
  Create, update, delete, and list labels for comprehensive label management.

• search_emails
  Search emails using various criteria (subject, sender, date range).

• list_emails_by_label
  List emails in inbox, sent, or custom labels.

• mark_read_unread
  Mark emails as read or unread.

• move_email
  Move emails to different labels/folders.

• delete_email
  Delete emails from the mailbox.

• batch_operations
  Efficiently process multiple emails at once with batch operations.

Use Cases of this MCP Server

• Automated Email Sending
  Developers can set up workflows that allow AI agents to compose and send emails automatically, reducing manual effort for routine communications.

• Inbox Triage and Management
  AI assistants can categorize, label, and move emails to appropriate folders, helping users maintain organized inboxes and prioritize important messages.

• Email Search and Retrieval
  With advanced search criteria, users can quickly locate specific messages or attachments, streamlining information retrieval from their Gmail accounts.

• Batch Processing
  Bulk operations such as deleting, marking read/unread, or moving groups of emails can be automated, saving time for users with high email volumes.

• Label Management Automation
  AI can create, update, or delete Gmail labels dynamically, enabling adaptive organization strategies based on evolving user needs or project requirements.

How to set it up

Windsurf

1. Ensure prerequisites such as Node.js are installed.
2. Open the Windsurf configuration file (commonly windsurf.json or similar).
3. Add the Gmail MCP Server package:

   {
     "mcpServers": {
       "gmail-mcp": {
         "command": "npx",
         "args": ["@gongrzhe/server-gmail-autoauth-mcp@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the setup by checking that the MCP server is listed in your Windsurf dashboard.

Securing API Keys Example:

{
  "mcpServers": {
    "gmail-mcp": {
      "command": "npx",
      "args": ["@gongrzhe/server-gmail-autoauth-mcp@latest"],
      "env": {
        "GOOGLE_CLIENT_ID": "your-client-id",
        "GOOGLE_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

Claude

1. Ensure Node.js and the Claude platform are set up.
2. Edit the Claude MCP configuration file.
3. Add the Gmail MCP Server:

   {
     "mcpServers": {
       "gmail-mcp": {
         "command": "npx",
         "args": ["@gongrzhe/server-gmail-autoauth-mcp@latest"]
       }
     }
   }
   

4. Save the configuration and restart Claude.
5. Confirm the server is active within Claude.

Environment Variable Example:

{
  "env": {
    "GOOGLE_CLIENT_ID": "your-client-id",
    "GOOGLE_CLIENT_SECRET": "your-client-secret"
  }
}

Cursor

1. Install Node.js and ensure Cursor is running.
2. Update the Cursor configuration to include the Gmail MCP Server:

   {
     "mcpServers": {
       "gmail-mcp": {
         "command": "npx",
         "args": ["@gongrzhe/server-gmail-autoauth-mcp@latest"]
       }
     }
   }
   

3. Restart Cursor for changes to take effect.
4. Verify integration by checking available MCP servers.

Cline

1. Prepare your environment with Node.js.
2. Add the Gmail MCP Server entry in Cline’s configuration:

   {
     "mcpServers": {
       "gmail-mcp": {
         "command": "npx",
         "args": ["@gongrzhe/server-gmail-autoauth-mcp@latest"]
       }
     }
   }
   

3. Save and restart Cline.
4. Check that the Gmail MCP Server is recognized in the interface.

Note:
Always store sensitive API keys or credentials as environment variables and not directly in the configuration files. Use the env property in your MCP server configuration for secure injection of credentials.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gmail-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent can now use this MCP as a tool with access to all its functions and capabilities. Remember to change “gmail-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available documentation, Gmail MCP Server is well-featured for Gmail workflow automation and integration but lacks explicit prompt templates and sampling/roots support documentation. Its security handling and tool/resource exposure are strong, so I’d rate this MCP a 7.5 out of 10 for completeness and developer readiness.

MCP Score