LM Studio MCP server

LMStudio-MCP creates a bridge between Claude (with MCP capabilities) and your locally running LM Studio instance. This allows Claude to communicate with your local LLM models, enabling you to leverage your private models through Claude's interface while combining Claude's capabilities with your own models.

Prerequisites

• Python 3.7+
• LM Studio installed and running locally with a model loaded
• Claude with MCP access
• Required Python packages

Installation

1. Clone the repository:

   git clone https://github.com/infinitimeless/LMStudio-MCP.git
   cd LMStudio-MCP
   

2. Install the required packages:

   pip install requests "mcp[cli]" openai
   

MCP Configuration

You can configure Claude to connect to this bridge in two ways:

Using directly from GitHub

{
  "lmstudio-mcp": {
    "command": "uvx",
    "args": [
      "https://github.com/infinitimeless/LMStudio-MCP"
    ]
  }
}

Using local installation

{
  "lmstudio-mcp": {
    "command": "/bin/bash",
    "args": [
      "-c",
      "cd /path/to/LMStudio-MCP && source venv/bin/activate && python lmstudio_bridge.py"
    ]
  }
}

Usage

1. Start your LM Studio application and ensure it's running on port 1234 (the default)

2. Load a model in LM Studio

3. If running locally (not using uvx), run the LMStudio-MCP server:

   python lmstudio_bridge.py
   

4. In Claude, connect to the MCP server when prompted by selecting "lmstudio-mcp"

Available Functions

The bridge provides several functions for interacting with your local models:

• health_check(): Verify if LM Studio API is accessible
• list_models(): Get a list of all available models in LM Studio
• get_current_model(): Identify which model is currently loaded
• chat_completion(prompt, system_prompt, temperature, max_tokens): Generate text from your local model

Troubleshooting

API Connection Issues

If Claude reports 404 errors when trying to connect to LM Studio:

• Ensure LM Studio is running and has a model loaded
• Check that LM Studio's server is running on port 1234
• Verify your firewall isn't blocking the connection
• Try using "127.0.0.1" instead of "localhost" in the API URL

Model Compatibility

If certain models don't work correctly:

• Some models might not fully support the OpenAI chat completions API format
• Try different parameter values (temperature, max_tokens) for problematic models
• Consider switching to a more compatible model if problems persist

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.