$ loading_
Run and manage Slurm jobs on Compute2 using plain English.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "RISBridge MCP" yet — see the docs or source repo.
Submit a Slurm job on WashU RIS Compute2 using 1 GPU, 8 CPUs, and 32GB RAM to run /home/user/train.py with a 12-hour time limit, and save logs to logs/train.out.
Creates and submits the matching Slurm job configuration, then returns the job ID and a summary of key settings.
Create an array job on Compute2 for all CSV files in data/samples, running analysis.R for each file with 4 CPUs and 16GB RAM, and write outputs to results/.
Builds and submits a batch-friendly array job, explaining input mapping, resource allocation, and output locations.
Check the status of my recent Slurm jobs on Compute2. If any are pending due to insufficient resources, explain why, and cancel job 123456.
Returns job status details, explains pending reasons, and cancels the specified job.
Manage SLURM clusters over SSH for jobs, monitoring, queues, and files.
Connect to Slurm clusters to inspect jobs, queues, and HPC scheduling tasks.
Monitor and manage Slurm GPU jobs, allocations, and logs across clusters.
Expose an OpenAI-compatible endpoint to access and orchestrate MCP tools.
Bridge RisalDash devices to MCP for sensor reading and relay control.
Authenticate, inspect capabilities, check credits, and run Risha.ai generation requests.