Signal MCP server

This MCP server integrates with signal-cli to enable AI agents to send and receive Signal messages. It provides a straightforward way to communicate via Signal within your automated workflows or applications.

Prerequisites

This project requires signal-cli to be installed and configured on your system before you can use the MCP server.

Installing signal-cli

1. Install signal-cli: Follow the official installation instructions

2. Register your Signal account:

   signal-cli -u YOUR_PHONE_NUMBER register
   

3. Verify your account with the code received via SMS:

   signal-cli -u YOUR_PHONE_NUMBER verify CODE_RECEIVED
   

For more detailed setup instructions, see the signal-cli documentation.

Installation

To install the Signal MCP server, use pip:

pip install -e .
# or use uv for faster installation
uv pip install -e .

Usage

Starting the Server

Run the MCP server by executing the main.py script with your Signal phone number:

./main.py --user-id YOUR_PHONE_NUMBER [--transport {sse|stdio}]

Replace YOUR_PHONE_NUMBER with the phone number you registered with signal-cli. You can optionally specify the transport method (sse or stdio).

Available Tools

The MCP server provides three main functions:

• send_message_to_user: Send a direct message to a Signal user
• send_message_to_group: Send a message to a Signal group
• receive_message: Wait for and receive messages with timeout support

Sending Messages

To send a message to an individual user, the AI agent would use the send_message_to_user function with the recipient's phone number and the message content.

To send a message to a group, the AI agent would use the send_message_to_group function with the group ID and message content.

Receiving Messages

The receive_message function allows the AI agent to wait for incoming messages. You can specify a timeout to control how long the server should wait before returning.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.