Freqtrade MCP Server

What does “Freqtrade” MCP Server do?

The Freqtrade MCP Server is a Model Context Protocol (MCP) server that integrates seamlessly with the Freqtrade cryptocurrency trading bot via its REST API. By serving as a bridge between AI assistants and the Freqtrade platform, it enables AI agents to perform automated trading operations, access real-time market data, manage trading strategies, and interact with trading accounts programmatically. This integration enhances the development and automation of trading workflows, allowing for tasks such as executing trades, querying balances, and monitoring trading performance, all orchestrated through AI-driven workflows. The Freqtrade MCP Server is ideal for developers and traders seeking to leverage AI for advanced trading automation and decision-making.

List of Prompts

No explicit prompt templates are mentioned in the repository.

List of Resources

No explicit resources are described in the repository.

List of Tools

No explicit tool list or server.py file is present, and no tool definitions are documented in the accessible files.

Use Cases of this MCP Server

• Automated Trading Execution
  Enables AI agents to execute buy and sell orders on the Freqtrade bot, automating trading strategies and reducing manual intervention.
• Portfolio Monitoring
  Allows developers to programmatically monitor portfolio performance, balances, and open positions, providing real-time insights for decision-making.
• Strategy Management
  Facilitates the management and switching of trading strategies via AI workflows, streamlining backtesting and deployment processes.
• Market Data Retrieval
  Grants AI access to up-to-date market data and price feeds through the Freqtrade REST API, supporting data-driven trading algorithms.

How to set it up

Windsurf

1. Prerequisites:
   Ensure Python 3.13+, Freqtrade (with REST API enabled), and Git are installed.
2. Clone the Repository:

   git clone https://github.com/kukapay/freqtrade-mcp.git
   cd freqtrade-mcp
   

3. Install Dependencies:

   pip install freqtrade-client mcp[cli]
   

4. Edit Windsurf Configuration:
   Add the following to your configuration file:

   "mcpServers": {
     "freqtrade-mcp": {
       "command": "uv",
       "args": [
         "--directory", "/your/path/to/freqtrade-mcp",
         "run",
         "__main__.py"
       ],
       "env": {
         "FREQTRADE_API_URL": "http://127.0.0.1:8080",
         "FREQTRADE_USERNAME": "your_username",
         "FREQTRADE_PASSWORD": "your_password"
       }
     }
   }
   

5. Save and Restart:
   Save your configuration and restart Windsurf. Verify the MCP server is running.

Claude

1. Prerequisites:
   Install Python 3.13+, Freqtrade, and Git.
2. Clone and Install:

   git clone https://github.com/kukapay/freqtrade-mcp.git
   cd freqtrade-mcp
   pip install freqtrade-client mcp[cli]
   

3. Edit Claude Configuration:
   Add the MCP server configuration as shown above in the appropriate JSON location.
4. Save and Restart:
   Ensure your changes are saved and restart Claude to activate the MCP server.

Cursor

1. Prerequisites:
   Python 3.13+, Freqtrade, and Git installed.
2. Clone and Install:

   git clone https://github.com/kukapay/freqtrade-mcp.git
   cd freqtrade-mcp
   pip install freqtrade-client mcp[cli]
   

3. Edit Cursor Configuration:
   Insert the following in your mcpServers section:

   "mcpServers": {
     "freqtrade-mcp": {
       "command": "uv",
       "args": [
         "--directory", "/your/path/to/freqtrade-mcp",
         "run",
         "__main__.py"
       ],
       "env": {
         "FREQTRADE_API_URL": "http://127.0.0.1:8080",
         "FREQTRADE_USERNAME": "your_username",
         "FREQTRADE_PASSWORD": "your_password"
       }
     }
   }
   

4. Save and Restart:
   Restart Cursor and verify the server is running.

Cline

1. Prerequisites:
   Python 3.13+, Freqtrade, and Git.
2. Clone and Install:

   git clone https://github.com/kukapay/freqtrade-mcp.git
   cd freqtrade-mcp
   pip install freqtrade-client mcp[cli]
   

3. Configure Cline:
   Add the following snippet to the mcpServers section:

   "mcpServers": {
     "freqtrade-mcp": {
       "command": "uv",
       "args": [
         "--directory", "/your/path/to/freqtrade-mcp",
         "run",
         "__main__.py"
       ],
       "env": {
         "FREQTRADE_API_URL": "http://127.0.0.1:8080",
         "FREQTRADE_USERNAME": "your_username",
         "FREQTRADE_PASSWORD": "your_password"
       }
     }
   }
   

4. Save and Restart:
   Save configuration and restart Cline. Confirm MCP integration.

Securing API Keys:
Store API credentials in environment variables within the configuration:

"env": {
  "FREQTRADE_API_URL": "http://127.0.0.1:8080",
  "FREQTRADE_USERNAME": "${FREQTRADE_USERNAME}",
  "FREQTRADE_PASSWORD": "${FREQTRADE_PASSWORD}"
},
"inputs": {
  "FREQTRADE_USERNAME": "your_username",
  "FREQTRADE_PASSWORD": "your_password"
}

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:

{
  "freqtrade-mcp": {
    "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 “freqtrade-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 above, the Freqtrade MCP server provides a clear overview and setup guidance, but lacks explicit documentation for prompts, resources, and tools in the public files. Its utility for integrating AI with Freqtrade is strong, but documentation depth lowers its completeness score.

MCP Score

Our opinion:
The Freqtrade MCP server is useful for automated trading workflows and AI integration, but would benefit from more comprehensive documentation around its available tools, prompt templates, and resources. Its setup instructions are clear, and it is open source, but its MCP feature coverage is incomplete for advanced users.

Rating: 4/10