Enables AI assistants to interact with a Mealie recipe database, providing tools for managing and accessing recipes stored in a Mealie instance.
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., "@Mealie MCP Serverfind recipes with chicken and broccoli"
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.
Mealie MCP Server (TypeScript)
This project enables AI assistants to interact with your Mealie recipe database through MCP clients such as Claude Desktop.
Based on rldiao/mealie-mcp-server - rewritten in TypeScript.
Installation
Or run directly with npx:
Prerequisites
Node.js 18+
Running Mealie instance with API key
Usage with Claude Desktop
Add the server to your claude_desktop_config.json:
WSL Users
If running on Windows with WSL:
Alternative: Local Installation
If you prefer to run from a local clone:
Development
Clone the repository and install dependencies:
Copy the environment template and configure:
Edit the
.envfile with your Mealie instance details:
Build the project:
Run the server:
License
This project is licensed under the MIT License - see the LICENSE file for details.