Cloudera AI MCP

The Cloudera ML Model Control Protocol (MCP) is a Python toolkit that provides functions for integrating with the Cloudera Machine Learning platform, including services such as file management, job scheduling, model management, and experiment tracking.

Developer tools Cloud platform #Machine learning #Platform integration #Model management #Job scheduling .Python

rating : 2 points

downloads : 6.4K

update time : 2025-04-29

Open Site

What is Cloudera MCP?

Cloudera MCP is a protocol server implemented in Python, providing a programmatic control interface for the Cloudera Machine Learning (CML) platform. It allows developers to manage resources such as files, jobs, models, and experiments in CML projects through APIs.

How to use Cloudera MCP?

You can use it in three ways: 1) Run as an independent server. 2) Integrate it into Python code. 3) Use it through the command-line tool. You only need to configure the CML instance URL and API key to start using it.

Use cases

Suitable for scenarios that require automated management of CML resources, such as continuous integration/deployment (CI/CD), batch job management, model lifecycle management, and resource synchronization during team collaboration.

Main features

File management

Supports uploading an entire folder while maintaining the directory structure and can ignore specified folders (e.g.,.git, node_modules, etc.)

Job control

Create, list, and delete CML jobs, and support batch deletion of all jobs

Project discovery

Find the project ID by project name and list the project file structure

Model management

Create and manage ML models and deployments, and support listing model and deployment information

Experiment tracking

Record and manage machine learning experiments and run records

Application management

Create, update, and manage CML applications

Advantages

Complete coverage of CML functions, supporting full lifecycle management of files, jobs, models, etc.

Flexible integration methods, supporting server mode, API calls, and command line

Powerful automation capabilities, suitable for integration into CI/CD processes

Upload function that retains the directory structure, facilitating project migration and collaboration

Limitations

Requires a Python 3.8+ environment

Depends on the CML platform and cannot be used independently

Some advanced features require a specific version of CML to support

How to use

Installation preparation

Clone the repository and install dependencies

Configure authentication

Set environment variables or directly configure the CML instance URL and API key in the code

Run the server

Start the MCP server for Claude or other clients to connect

Integrated use

Import and use MCP functions in Python code

Usage examples

Project initialization

Synchronize the local development environment to a CML project

Automated model training

Create a model training job that runs on a schedule

Batch cleanup

Delete all completed jobs

Frequently Asked Questions

How to get an API key?

What should I do if uploading a large file fails?

How to integrate with the Claude desktop application?

Which Python versions are supported?

Related resources

Cloudera official documentation

Official documentation for Cloudera Machine Learning

GitHub repository

Project source code and the latest version

Python requests library documentation

Documentation for the HTTP request library that MCP depends on

🚀 Cloudera Machine Learning Model Control Protocol (MCP)

This MCP enables the integration of Python with Cloudera Machine Learning, allowing Claude to interact with CML services programmatically.

🚀 Quick Start

This MCP implementation allows seamless interaction between Python and Cloudera Machine Learning, enabling Claude to communicate with CML services programmatically.

✨ Features

Upload Folders: Upload entire folders to your CML project while preserving the directory structure.
Create Jobs: Create new CML jobs with custom settings.
List Jobs: View all jobs in a project and their current status.
Delete Jobs: Delete a single job or all jobs in a project.
Get Project ID: Retrieve the project ID by project name.
List Project Files: View files and directories in a project.
Model Management: Create, list, and manage ML models and deployments.
Experiment Tracking: Record and manage ML experiments and runs.
Application Management: Create, update, and manage CML applications.

📦 Installation

Clone this repository.
Install the dependencies:
```
pip install -r requirements.txt
```

📚 Documentation

Configuration

MCP requires the following configuration:

host: The URL of your CML instance (e.g., "https://ml-xxxx.cloudera.site").
api_key: The API key for authentication.
project_id: Your CML project ID (optional - can now be obtained by project name).

You can provide this configuration via code when initializing MCP or use environment variables:

export CLOUDERA_ML_HOST="https://ml-xxxx.cloudera.site"
export CLOUDERA_ML_API_KEY="your-api-key"
# Optional: export CLOUDERA_ML_PROJECT_ID="your-project-id"

URL Configuration Notes

The host URL should not contain a duplicate "https://" prefix.
Trailing slashes are handled automatically.
MCP will automatically format the URL correctly.

Running the MCP Server

This MCP can be run as a server, allowing Claude to interact with Cloudera ML.

Set up the Environment

Copy the example .env file and add your credentials:

cp .env.example .env
# Edit the .env file to provide your credentials

Start the Server

./server.py

The server uses stdio transport and can be directly connected to Claude by default.

Using with Claude Desktop

To use this server with the Claude Desktop application, add the following configuration to the "mcpServers" section of claude_desktop_config.json:

{
  // Other configurations...
  "mcpServers": {
    "my-mcp-server": {
      "type": "stdio",
      "command": ["python", "-m", "cloudera.mcp.server"],
      "args": []
    }
  }
}