Ollama MCP server

Bridges to Ollama, enabling local language model capabilities for writing assistance, code generation, and data analysis.
Back to servers
Setup instructions
Provider
Vincent F
Release date
Jan 24, 2025
Language
Python
Stats
3 stars

This MCP server enables Claude Desktop to communicate with Ollama LLM server, allowing you to use Ollama models directly through the Claude interface.

Installation

Follow these simple steps to get the MCP server up and running:

  1. Clone the repository to your local machine

    git clone https://github.com/username/mcp-server-ollama.git
    cd mcp-server-ollama
    
  2. Create your environment configuration file

    cp .env.example .env
    
  3. Edit the .env file with your preferred text editor to configure as needed

  4. Install the required dependencies

    pip install -r requirements.txt
    

Configuration with Claude Desktop

To use this MCP server with Claude Desktop, you'll need to edit the Claude Desktop configuration file:

  1. Locate or create the claude_desktop_config.json file

  2. Add the following content to the file:

    {
      "mcpServers": {
        "ollama-server": {
          "command": "python",
          "args": ["-m", "src.mcp_server.server"],
          "env": {
            "PYTHONPATH": "path-to-mcp-server"
          }
        }
      }
    }
    
  3. Replace path-to-mcp-server with the absolute path to the MCP server repository on your system

Usage

Once configured, Claude Desktop will automatically start the MCP server when needed. This allows you to:

  • Access your locally running Ollama models through the Claude Desktop interface
  • Use Ollama's models with Claude's user-friendly interface
  • Switch between different local models as needed

The server runs in the background and handles the communication protocol between Claude Desktop and your Ollama installation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ollama-server" '{"command":"python","args":["-m","src.mcp_server.server"],"env":{"PYTHONPATH":"path-to-mcp-server"}}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "ollama-server": {
            "command": "python",
            "args": [
                "-m",
                "src.mcp_server.server"
            ],
            "env": {
                "PYTHONPATH": "path-to-mcp-server"
            }
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ollama-server": {
            "command": "python",
            "args": [
                "-m",
                "src.mcp_server.server"
            ],
            "env": {
                "PYTHONPATH": "path-to-mcp-server"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later