WhatsApp MCP Server Integration

What does “WhatsApp” MCP Server do?

The WhatsApp MCP (Model Context Protocol) Server acts as a bridge between AI assistants and your personal WhatsApp account. By connecting via the WhatsApp web multidevice API (using the whatsmeow library), it enables AI models such as Claude or Cursor to search and read your personal WhatsApp messages (including images, videos, documents, and audio), search contacts, and send messages to individuals or groups. All interactions are handled locally: your message history is stored in a SQLite database, and data is only shared with the AI agent when explicitly accessed through standardized tools. This setup allows developers and users to manage WhatsApp communications programmatically, automate messaging workflows, and integrate WhatsApp data into broader development or productivity processes—all while maintaining user control over data access.

List of Prompts

No prompt templates are mentioned in the available documentation.

List of Resources

• The documentation does not explicitly list MCP resources exposed by the server.

List of Tools

• search_contacts: Search for WhatsApp contacts by name or phone number.
• list_messages: Retrieve WhatsApp messages with optional filters and context parameters.
• list_chats: List all available chats with their metadata.
• get_chat: Get detailed information about a specific chat.

Use Cases of this MCP Server

• WhatsApp Message Search and Retrieval
  Developers and AI agents can programmatically search and retrieve WhatsApp messages, including multimedia content, for review, reporting, or archiving.

• Automated Messaging
  Enables sending messages or media files (images, videos, documents, audio) to individuals or groups through AI workflows, facilitating reminders, notifications, or bulk communication.

• Contact Management
  Supports searching and organizing WhatsApp contacts via the AI, enhancing productivity for users who manage large contact lists.

• Chat Analytics
  By listing and analyzing metadata from chats and messages, developers can perform analytics or create dashboards on messaging patterns, group activity, or communication trends.

• Integration with AI Assistants
  Allows seamless interaction between WhatsApp and AI models (like Claude or Cursor), leveraging AI to summarize chats, draft responses, or automate repetitive tasks.

How to set it up

Windsurf

No setup instructions for Windsurf are provided in the documentation.

Claude

1. Prerequisites: Install Go, Python 3.6+, UV (Python package manager), and optionally FFmpeg.
2. Clone the repository:

   git clone https://github.com/lharries/whatsapp-mcp.git
   cd whatsapp-mcp
   

3. Run the WhatsApp bridge:

   cd whatsapp-bridge
   go run main.go
   

   Authenticate via QR code using your WhatsApp mobile app.
4. Configure MCP server:
   Save the following JSON to ~/Library/Application Support/Claude/claude_desktop_config.json:

   {
     "mcpServers": {
       "whatsapp": {
         "command": "{{PATH_TO_UV}}",
         "args": [
           "--directory",
           "{{PATH_TO_SRC}}/whatsapp-mcp/whatsapp-mcp-server",
           "run",
           "main.py"
         ]
       }
     }
   }
   

5. Restart Claude Desktop: Open Claude to see WhatsApp as an available integration.

Note about securing API keys: No explicit API keys are used, but if needed, environment variables can be set via an env block in the JSON configuration.

Example with environment variable:

{
  "mcpServers": {
    "whatsapp": {
      "command": "{{PATH_TO_UV}}",
      "args": [
        "--directory",
        "{{PATH_TO_SRC}}/whatsapp-mcp/whatsapp-mcp-server",
        "run",
        "main.py"
      ],
      "env": {
        "MY_API_KEY": "your_api_key_here"
      },
      "inputs": {
        "api_key": "${MY_API_KEY}"
      }
    }
  }
}

Cursor

1. Prerequisites: Same as above.
2. Clone and run the bridge: Follow steps as with Claude.
3. Configure MCP server:
   Save the following JSON to ~/.cursor/mcp.json:

   {
     "mcpServers": {
       "whatsapp": {
         "command": "{{PATH_TO_UV}}",
         "args": [
           "--directory",
           "{{PATH_TO_SRC}}/whatsapp-mcp/whatsapp-mcp-server",
           "run",
           "main.py"
         ]
       }
     }
   }
   

4. Restart Cursor to activate the integration.

Note about securing API keys: Use the same environment variable approach as with Claude if necessary.

Cline

No setup instructions for Cline are provided in the documentation.

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:

{
  "whatsapp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “whatsapp” 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, WhatsApp MCP Server is well-documented for general setup and tool usage but lacks explicit information about resources, prompt templates, roots, and sampling support. The project is mature (licensed, popular, and actively maintained), but missing some MCP-specific advanced documentation.

Our opinion

We would rate this MCP server a 7/10—it is robust, popular, and clear for practical integration, but would benefit from more comprehensive MCP resource, prompt, and advanced feature documentation.

MCP Score