Mage.ai MCP Integration
About
# Mage.ai MCP Integration A comprehensive Model Context Protocol (MCP) integration for [Mage.ai](https://mage.ai/), allowing AI assistants like Anthropic's Claude to efficiently work with Mage data pipelines. ## Features - **Browse Pipelines**: Explore all Mage.ai pipelines and their components - **View and Edit…
Details
- License
- MIT
Explore
- Browse Pipelines: Explore all Mage.ai pipelines and their components
- View and Edit Code: Read and modify block code
- Execute Pipelines: Run entire pipelines or individual blocks
- Search Functionality: Find blocks by name, type, or content
- Pipeline Creation: Create new pipelines and blocks from scratch
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mage.ai MCP IntegrationCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
pip install -r requirements.txt
Use the provided script to start the MCP server:
For the best experience, install this server directly with Claude Desktop:
mcp install run_server.py -v MAGE_API_URL=http://localhost:6789/api/ -v MAGE_API_KEY=your_key
```
- list_all_pipelines() - List all pipelines with details
- get_pipeline_details(pipeline_uuid) - Get pipeline information
- list_pipeline_blocks(pipeline_uuid) - List blocks in a pipeline
- get_block_content(pipeline_uuid, block_uuid) - Get block code
- create_pipeline(name, description, pipeline_type) - Create a new pipeline
- create_block(pipeline_uuid, name, block_type, language, content, upstream_blocks) - Create a block
- update_block_content(pipeline_uuid, block_uuid, content) - Update block code
- execute_pipeline(pipeline_uuid) - Run a pipeline
- execute_block(pipeline_uuid, block_uuid) - Run a specific block
- get_pipeline_code(pipeline_uuid) - Get complete pipeline code
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mage.ai mcp integration": {
"mage-mcp-server": {
"command": "python",
"args": [
"run_server.py"
]
}
}
}
}McpServers
{
"mage-mcp-server": {
"command": "python",
"args": [
"run_server.py"
]
}
}A comprehensive Model Context Protocol (MCP) integration for Mage.ai, allowing AI assistants like Anthropic's Claude to efficiently work with Mage data pipelines.
Features
- Browse Pipelines: Explore all Mage.ai pipelines and their components
- View and Edit Code: Read and modify block code
- Execute Pipelines: Run entire pipelines or individual blocks
- Search Functionality: Find blocks by name, type, or content
- Pipeline Creation: Create new pipelines and blocks from scratch
Installation
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
