list_projectsLABSCO SUMMARY
The CML loop — edit, run, check — without the web UI.
It covers the whole cycle a data scientist repeats all day: change a file in the project, turn it into a job, run it, read the run. Because file patching is a tool of its own, an assistant can fix and re-run without a full upload each time.
What it is
A standalone MCP server for Cloudera Machine Learning, covering projects, project files, jobs and runs against a CML instance you name.
What you get
- Projects listed, created and inspected without opening the CML web interface
- Project files read, uploaded, renamed and patched in place — targeted edits rather than re-uploading a whole file
- Jobs created from scratch or straight from a file in the project, then listed and inspected
- Job execution controlled end to end: run now, schedule, list previous runs, stop a run that is going wrong
- The available runtime addons listed, so a job is configured against what the instance actually offers
- SSL certificate download for instances using a self-signed certificate
Requirements
Python 3.8+ with the MCP CLI package and requests. The instance is addressed by its host URL and an API token, given as environment variables — the server accepts more than one naming scheme — or as the same values on the launch command. Self-signed instances need the certificate downloaded and the server pointed at that file.
Setup effort
Build from source — git clone https://github.com/yw449/cloudera-cml-mcp-server.git
USE CASES
01
Standing up a new project and its first job
Create the project, upload the script, and turn that file directly into a job — three steps that normally mean three screens.
02
Fixing a script that just failed
Read the file, patch the lines that broke, and start the job again without leaving the conversation.
03
Finding out what happened overnight
List the runs of a job and inspect the ones that matter, instead of scrolling the runs page.
04
Putting a job on a schedule
Schedule an existing job so a recurring task stops depending on somebody remembering to press run.
05
Stopping a run that is burning resources
Cancel the run in progress as soon as the output shows it is going nowhere.
06
Tidying a project's files
List what is there, rename what is misnamed, and read anything you are unsure about before changing it.
17 tools
Listed in project docs. Your client may show a different list.
create_projectget_projectlist_filesread_fileupload_filerename_filepatch_filelist_jobscreate_jobcreate_job_from_filerun_joblist_job_runsstop_job_runschedule_joblist_runtime_addonsdownload_ssl_certBEFORE YOU INSTALL
What to know first
Tools you get
17 tools named in the project's documentation.
Requires
- Python 3.8+
- CLOUDERA_ML_API_KEY in your environment
- CLOUDERA_ML_HOST in your environment
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/yw449/cloudera-cml-mcp-server.git
pip install "mcp[cli]" requestsMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"cml": {
"command": "uv",
"args": [
"run",
"<YOUR_PATH_TO_CLOUDERA_CML_MCP_SERVER>/cml_mcp_server/cml_mcp_server.py"
],
"env": {
"CLOUDERA_ML_HOST": "https://<YOUR_CML_INSTANCE>.cloudera.com",
"CLOUDERA_ML_API_KEY": "<YOUR_CLOUDERA_ML_API_KEY>"
}
}
}
}
