dominodatalab/domino_mcp_server

이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기

3 stars 5 forks 품질 56 트렌드 10

This project provides a Model Context Protocol (MCP) server that when combined with AI coding tools like Cursor allows you to build models via agentic code automation, run training jobs, track...

개요

This project provides a Model Context Protocol (MCP) server that when combined with AI coding tools like Cursor allows you to build models via agentic code automation, run training jobs, track experiments, optimize models, and perform exploratory data analysis leveraging the Domino Data Lab platform. Accelerating data science work doesn't just happen by involving an AI Coding assistant in writing python scripts, but also by involving the AI agent in the full development, validation and optimization lifecycle. By using a "vibe modeling" approach combined with Domino's Enterprise AI Platform, Every iteration an AI co-pilot performs is automatically tracked and is reproducible in Domino. This addresses the core challenge of governance in the AI tools era. More information about MCP Servers with Cursor can be found here. * Execute commands (e.g., Python scripts) as jobs within a specified Domino project. * Retrieve the status and results of a specific Domino job run.

README

원문 README의 일부입니다. 원문 보기.

Domino MCP Server

By using a “vibe modeling” approach combined with Domino’s Enterprise AI Platform, Every iteration an AI co-pilot performs is automatically tracked and is reproducible in Domino. This addresses the core challenge of governance in the AI tools era.

More information about MCP Servers with Cursor can be found here.

LLM tools of the MCP Server

Run Domino Jobs: Execute commands (e.g., Python scripts) as jobs within a specified Domino project.
Check Job Status: Retrieve the status and results of a specific Domino job run.
Check Job Results: Retrieve the status and results of a specific Domino job run.

How it Works

The domino_mcp_server.py script uses the fastmcp library to define an MCP server. It exposes two functions (run_domino_job and check_domino_job_run_result) as tools that Cursor can call. These functions make authenticated REST API calls to the Domino platform using the DOMINO_API_KEY and DOMINO_HOST loaded from the .env file (local to the mcp server not your cursor project).

The server is configured to run using stdio transport, meaning Cursor starts and manages the Python script process locally (using uv run) and communicates with it via standard input/output.

Setup

Clone the Repository:

# If you haven't already, clone the repository containing this server
git clone https://github.com/dominodatalab/domino_mcp_server.git
cd domino_mcp_server

Install Dependencies: This server requires Python and the fastmcp and requests libraries. Ensure you have uv installed (https://github.com/astral-sh/uv). Install the dependencies using uv:
```
uv pip install -e .
```
Set API Key and Host URL using .env file: The server needs your Domino API key and host URL to authenticate requests and connect to your Domino instance. Obtain your API key from your Domino account settings. Create a file named .env in the root directory of this project (the same directory as domino_mcp_server.py) and add the following lines, replacing the values with your actual credentials:
```
DOMINO_API_KEY='your_api_key_here'
DOMINO_HOST='https://your-domino-instance.com'
```
Note: Ensure .env is added to your .gitignore file to prevent accidentally committing your API key and host URL.
Configure Cursor:

GitHub에서 전체 README 보기

설치

This server does not publish a one-line install command.

Open the repository installation guide MCP 초보자라면? mcpskill.org 가이드부터 시작하세요 →

설정

{
            "mcpServers": {
                "domino_server": {
                "command": "uv",
                "args": [
                    "--directory",
                    "/full/directory/path/to/domino_mcp_server",
                    "run",
                    "domino_mcp_server.py"
                ] 
                }
            }
        }