Leonardo AI MCP server

The Leonardo MCP Server is a versatile tool that enables AI models to interact with Leonardo AI's image generation capabilities through the Model Context Protocol. It allows you to create image generation jobs, check available models, monitor job status, and retrieve user jobs using either HTTP or stdio communication methods.

Installation Requirements

Before installing, you need to generate a Leonardo API key:

1. Visit the Leonardo AI platform to create your API key
2. Set this key in the environment variable LEONARDO_API_KEY

Setting Up for Different Clients

For JSON Config-Based Clients

If you're using Claude Desktop, Cursor, or other MCP clients that use JSON configuration files, add the following to your config:

{
  "mcpServers": {
    "leonardo-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/ish-joshi/leonardo-mcp-server",
        "leonardo-mcp-server",
        "stdio"
      ],
      "env": {
        "LEONARDO_API_KEY": "YOUR_LEONARDO_API_KEY"
      }
    }
  }
}

Running the Server

The Leonardo MCP Server supports two operational modes to accommodate different client needs:

HTTP Mode

This is the default mode and is ideal for remote clients like ChatGPT Playground or browser-based tools:

uvx --from git+https://github.com/ish-joshi/leonardo-mcp-server leonardo-mcp-server

For remote clients, you'll need to expose your local server to the internet using a tunneling service like ngrok:

ngrok http 8080

After running this command, copy the public URL provided by ngrok and use it as the endpoint in your client application.

Stdio Mode

This mode is suitable for local clients that communicate via standard input/output:

uvx --from git+https://github.com/ish-joshi/leonardo-mcp-server leonardo-mcp-server stdio

Configuration Options

Environment Variables

• LEONARDO_API_KEY (required): Your personal Leonardo AI API key

Using the Server

Once running, the Leonardo MCP Server provides several capabilities:

• Create new image generation jobs with Leonardo AI
• View all available image generation models
• Check the status of your pending or completed image generation jobs
• Retrieve all image generation jobs associated with your account

Your AI client can now seamlessly generate images through Leonardo AI by communicating with this MCP server.

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 "leonardo-mcp-server" '{"command":"uvx","args":["--from","git+https://github.com/ish-joshi/leonardo-mcp-server","leonardo-mcp-server","stdio"],"env":{"LEONARDO_API_KEY":"YOUR_LEONARDO_API_KEY"}}'

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": {
        "leonardo-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/ish-joshi/leonardo-mcp-server",
                "leonardo-mcp-server",
                "stdio"
            ],
            "env": {
                "LEONARDO_API_KEY": "YOUR_LEONARDO_API_KEY"
            }
        }
    }
}

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": {
        "leonardo-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/ish-joshi/leonardo-mcp-server",
                "leonardo-mcp-server",
                "stdio"
            ],
            "env": {
                "LEONARDO_API_KEY": "YOUR_LEONARDO_API_KEY"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect