Leonardo MCP Server
Recommended for exposing the local server to the internet when running in HTTP mode, allowing remote clients to connect to the Leonardo AI integration.
The server includes a video demo hosted on YouTube that showcases its functionality.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Leonardo MCP Servergenerate an image of a futuristic city at sunset"
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.
Leonardo MCP Server
A Model Context Protocol (MCP) server for Leonardo AI, supporting both HTTP and stdio modes.
Features
Create image generation jobs with Leonardo AI
See available models
Check the status of image generation jobs
Get all the user's image generation jobs
Supports both
HTTPandstdiotransports
Related MCP server: Image Toolkit MCP Server
Installation
JSON Config
Support for Claude Desktop, Cursor and other MCP clients that use JSON config files.
You will need to generate a Leonardo API key and set it in the environment variable LEONARDO_API_KEY before running the server.
{
"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"
}
}
}
}Demo

Running Modes
This server supports two modes:
HTTP mode (default):
Suitable for remote clients (e.g., ChatGPT Playground, browser-based tools).
The server runs an HTTP endpoint. You must expose it to the internet if your client is remote.
Stdio mode:
Suitable for local clients that communicate over standard input/output (stdio).
No network port is opened.
HTTP Mode (for remote clients)
Start the server in HTTP mode (default):
uvx --from git+https://github.com/ish-joshi/leonardo-mcp-server leonardo-mcp-serverIf your client is remote (e.g., ChatGPT Playground), you must expose your local server to the internet. You can use ngrok or a similar tunneling tool:
ngrok http 8080Copy the public URL from ngrok and use it as the endpoint in your client.
Stdio Mode (for local clients)
Start the server in stdio mode:
uvx --from git+https://github.com/ish-joshi/leonardo-mcp-server leonardo-mcp-server stdioEnvironment Variables
LEONARDO_API_KEY(required): Your Leonardo AI API key.
Development
Edit
main.pyto add or modify MCP tools.Run using
python main.pyand test with a compatible MCP client. I prefer to use 5ire MCP client for testing.See python-sdk documentation for more info.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Generate AI images and videos from any compatible MCP client.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Related MCP Servers
- AlicenseCqualityCmaintenanceA Model Context Protocol server that provides image generation capabilities using the Ideogram API, allowing users to create images from text prompts with customizable parameters.1105MIT
- AlicenseNot gradedqualityFmaintenanceA server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.18MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server enabling AI assistants to generate images through OpenAI's DALL-E API with full support for all available options and fine-grained control.151MIT
- AlicenseDqualityFmaintenanceA Model Context Protocol server that enables generating and editing images using OpenAI's gpt-image-1 model, allowing AI assistants to create and modify images from text prompts.28418MIT