Which integrations are available for this server?

Enables AI agents to access Signal Desktop chat messages and attachments, providing tools to list chats, retrieve message history with pagination, and search for specific text within conversations from your local Signal database.

How do I use signal-mcp-server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@signal-mcp-server show me my recent messages with John Doe" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

📱 signal-mcp-server

MCP Server for retrieving Signal messages using signal-export logic.

🎯 Overview

This MCP server enables AI agents and tools to access Signal Desktop chat messages and attachments via the Model Context Protocol (MCP).

Related MCP server: mcp-server-collector

🛠️ Features

Retrieve Signal messages from your local Signal Desktop database
List all Signal chats with contact details and message counts
Filter messages by chat/contact name
Paginate through message history with offset and limit
Support for multiple operating systems (Windows, macOS, Linux)
Handle encrypted Signal databases

📋 Prerequisites

Python 3.13 or higher
UV package manager
Signal Desktop installed with existing message database
Node.js and npm (for MCP inspector tools)
Windows, macOS, or Linux operating system

1. Signal Desktop

Official Download Page:
https://signal.org/download/
Direct Download Links:

Note: Signal Desktop requires Signal to be installed on your phone for initial setup.

2. Python

Official Download Page:
https://www.python.org/downloads/
Direct Download for Python 3.13.5:
Python 3.13.5 Release Page
Download the installer for your OS (Windows, macOS, Linux) and follow the setup instructions.

3. UV (Python Package Manager)

Official Documentation & Source:
https://github.com/astral-sh/uv
UV Documentation
Installation (Windows):
```
irm https://astral.sh/uv/install.ps1 | iex
```
Or, using pip (if you already have Python and pip installed):
```
pip install uv
```

Installation (macOS/Linux):

curl -LsSf https://astral.sh/uv/install.sh | sh

More Info:
UV Installation Guide

4. Claude Desktop

Official Download Page:
https://claude.ai/download
Download the installer for your OS (Windows, macOS) and follow the setup instructions.

🚀 Installation Signal MCP Server

Clone the repository:

git clone https://github.com/stefanstranger/signal-mcp-server.git
cd signal-mcp-server

Create a virtual environment:
```
uv venv .venv --python 3.13
```
Activate the virtual environment:
- Windows PowerShell:
  .\.venv\Scripts\Activate.ps1
- macOS/Linux:
  source .venv/bin/activate
Install dependencies:
```
uv pip install fastmcp signal-export
```

⚙️ Configuration

🔧 Claude Desktop Setup

Usage with Claude Desktop Add the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "signal-mcp-server": {
         "type": "stdio",
         "command": "uv",
         "args": [
            "run",
            "--with",
            "mcp[cli]",
            "--with",
            "signal-export",
            "mcp",
            "run",
            "C:\\Github\\signal-mcp-server\\server.py"
         ]
    }
  }
}

Signal Data Directory

The server automatically detects your Signal data directory based on your operating system:

Windows: %APPDATA%\Signal
macOS: ~/Library/Application Support/Signal
Linux: ~/.config/Signal (or Flatpak: ~/.var/app/org.signal.Signal/config/Signal)

Encryption

If your Signal database is encrypted, you may need to provide:

password: Database password (if set)
key: Encryption key (if required)

🏃 Running the Server

Start MCP Server

uv run .\server.py

Inspect MCP Server

Using the MCP Inspector:

npx @modelcontextprotocol/inspector uv run --with mcp[cli] mcp run c://github//signal-mcp-server//server.py

Using mcptools:

mcptools web cmd /c "uv.exe run --with mcp[cli] --with signal-export mcp run c:\\github\\signal-mcp-server\\server.py"

📖 Available Tools

1. `signal_list_chats`

Lists all Signal chats with their details.

Parameters:

source_dir (optional): Custom Signal data directory path
password (optional): Database password
key (optional): Encryption key
include_empty (optional): Include chats with no messages
include_disappearing (optional): Include disappearing messages

Example Response:

[
  {
    "name": "John Doe",
    "number": "+1234567890",
    "ServiceId": "abc123...",
    "total_messages": 150
  }
]

2. `signal_get_chat_messages`

Retrieves messages from a specific chat by name.

Parameters:

chat_name (required): Name of the chat contact
limit (optional): Maximum number of messages to return
offset (optional): Number of messages to skip (for pagination)
Other parameters same as signal_list_chats

Example Response:

[
  {
    "date": "2025-07-31T10:30:00",
    "sender": "John Doe",
    "body": "Hello! How are you?",
    "quote": "",
    "reactions": [],
    "attachments": []
  }
]

3. `signal_search_chat`

Search for specific text within Signal chat messages.

Parameters:

chat_name (required): Name of the chat to search within
query (required): Text to search for in message bodies
limit (optional): Maximum number of matching messages to return
source_dir (optional): Custom Signal data directory path
password (optional): Database password
key (optional): Encryption key
include_empty (optional): Include chats with no messages
include_disappearing (optional): Include disappearing messages

Example Response:

[
  {
    "date": "2025-07-31T10:30:00",
    "sender": "John Doe", 
    "body": "Let's meet at the coffee shop tomorrow",
    "quote": "",
    "reactions": [],
    "attachments": []
  }
]

🎯 Available Prompts

The server includes pre-built prompts for common analysis tasks:

1. `signal_summarize_chat_prompt`

Generate a summary prompt for recent messages in a specific chat.

2. `signal_chat_topic_prompt`

Generate a prompt to analyze discussion topics in a chat.

3. `signal_chat_sentiment_prompt`

Generate a prompt to analyze message sentiment in a chat.

4. `signal_search_chat_prompt`

Generate a search prompt for finding specific text in a chat.

💡 Usage Examples

List all chats

"List all Signal chats please"

Get recent messages from a specific chat

"Show me the last 10 messages from the Family group chat"

Search for topics in a chat

"What are the main topics discussed in the Work Team chat?"

Summarize conversations

"Summarize the recent conversation with John Doe"

Search within a chat

"Search for messages containing 'meeting' in the Work Team chat"

Analyze chat sentiment

"Analyze the sentiment of recent messages with Sarah"

🔒 Security & Privacy

⚠️ Important: This server provides access to your personal Signal messages. Please:

Only run this server locally
Never expose it to the internet
Be cautious about which AI agents you grant access
Consider the privacy of others in your conversations
Delete any exported data when no longer needed

🐛 Troubleshooting

Common Issues

"Signal database not found"
- Ensure Signal Desktop is installed
- Check if the data directory path is correct
- Verify you have read permissions
"Database is encrypted"
- Signal databases may be encrypted on some systems
- You may need to provide encryption credentials
"No messages found"
- Verify the chat name is spelled correctly
- Check if the chat has any messages
- Try using include_empty=True parameter
"Signal-MCP-Server does not want to start in Claude Desktop"
- Check if there are no other Python versions installed besides the recommended version 3.13.
- You may need to uninstall older Python versions installed.

📚 References

🙏 Credits

This project builds upon the excellent work of the signal-export project by Chris Arderne. The core logic for accessing and reading Signal Desktop databases is derived from and inspired by the signal-export library. I'm grateful for Chris his open-source contribution that made this MCP server possible.

📄 License

MIT License

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

⚖️ Disclaimer

This tool is not affiliated with or endorsed by Signal. Use at your own risk and respect the privacy of your conversations.

This server cannot be installed

-

security - not tested

F

license - not found

-

quality - not tested

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Report Issue

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

📱 signal-mcp-server

🎯 Overview

🛠️ Features

📋 Prerequisites

1. Signal Desktop

2. Python

3. UV (Python Package Manager)

4. Claude Desktop

🚀 Installation Signal MCP Server

⚙️ Configuration

🔧 Claude Desktop Setup

Signal Data Directory

Encryption

🏃 Running the Server

Start MCP Server

Inspect MCP Server

📖 Available Tools

1. signal_list_chats

2. signal_get_chat_messages

3. signal_search_chat

🎯 Available Prompts

1. signal_summarize_chat_prompt

2. signal_chat_topic_prompt

3. signal_chat_sentiment_prompt

4. signal_search_chat_prompt

💡 Usage Examples

List all chats

Get recent messages from a specific chat

Search for topics in a chat

Summarize conversations

Search within a chat

Analyze chat sentiment

🔒 Security & Privacy

🐛 Troubleshooting

Common Issues

📚 References

🙏 Credits

📄 License

🤝 Contributing

⚖️ Disclaimer

Resources

Looking for Admin?

Latest Blog Posts

MCP directory API

1. `signal_list_chats`

2. `signal_get_chat_messages`

3. `signal_search_chat`

1. `signal_summarize_chat_prompt`

2. `signal_chat_topic_prompt`

3. `signal_chat_sentiment_prompt`

4. `signal_search_chat_prompt`