Snapshot of local SSH-auth state (key, managed config, mux master) and whether the agent can run RIS commands hands-free. deep=true also runs the decisive key-only login test.

Create the dedicated ed25519 key (chmod 600) if absent and show the public key + install command. The private key is never returned. Pass overwrite=true to replace an existing key.

Print the dedicated public key and its fingerprint. The private key is never read.

Render the managed ~/.ssh/config block (with multiplexing) and a diff. Does NOT write anything.

Write the managed config block to ~/.ssh/config (atomic, backed up). Requires confirm=true.

Run the decisive key-only SSH test (BatchMode, no password/keyboard-interactive). Classifies whether the agent can automate without you, or whether Duo/MFA requires the multiplexing fallback.

Best-effort open of the ControlMaster session; on a Duo host it returns the exact interactive command to run in a real terminal (approve Duo once, then the agent reuses the socket).

Check the ControlMaster via ssh -O check AND a functional ssh true probe.

Remove ONLY the exact, verified stale ControlPath socket (five safety guards). Use when the master is gone but a dead socket blocks reconnection.

Personalized, plain-English setup checklist. It inspects your current state (WashU username, SSH key, SSH config, Duo/hands-free auth, account & workspace) and tells you the single next step. Read-only — it never changes anything; it points you at the exact tool or command to run next.

Read-only probe of your RIS identity: username, Slurm accounts/QOS, and WRITABLE storage workspaces (derived from your groups and live-tested). Presents candidates and asks you to confirm — it never picks for you.

Save your confirmed username + Slurm account + storage workspace to ~/.risbridge-mcp/config.json. Validates the account is yours and the workspace is writable (unless force). Requires confirm=true.

Show the active resolved profile (username, account, workspace, partitions) and the profiles saved in config.json.

Check the current profile against RIS facts: username set, account/workspace configured, partitions valid.

Show RIS Compute2 partitions with availability and plain-English notes (MIG vs full H100, preempt, no plain general).

Per-node H100 free/used on the GPU partition (full H100s only; MIG slices excluded).

Create the standard project directory tree (src/ data/{raw,interim,processed}/ models/ outputs/ logs/ sbatch/ envs/ configs/ checkpoints/ manifests/ tmp/) under your /storage workspace.

Write a text file into a safe project subdirectory (src/ data/ configs/ sbatch/ envs/ manifests/). Refuses overwrite unless overwrite=true. Binary content is not supported.

List files in a project (or a subdir) with depth and entry caps.

Read a run's manifest JSON from project/manifests, or list available manifests. Cross-references local run history.

Turn an intent into a safe, validated resource plan (CPU vs GPU, partition, cpus/mem/gpus/walltime, smoke-test recommendation) in plain English. Does NOT submit.

For non-HPC users: from a plain-English goal and a few optional hints, infer a safe plan and the exact next ris_submit_* call. Does NOT submit.

One call: ensures your project + environment exist (auto-builds a PyTorch/TF env if missing) and submits your script — GPU or CPU. No manual conda steps. dryRun preview by default; re-call with dryRun=false, confirm=true to run.

Run a project .py file as a batch job (CPU, or GPU if gpuCount>0). dryRun preview by default.

Run a project .R file via Rscript as a CPU batch job.

Execute a project .ipynb headlessly (nbconvert) as a batch job.

Submit a tiny GPU validation job (nvidia-smi + torch CUDA check). Uses a MIG slice on general-short by default, or a full H100 on general-gpu if fullH100=true.

Run a project script across a bounded Slurm array (the script reads $SLURM_ARRAY_TASK_ID). Total tasks capped at 10000.

Single-node multi-GPU PyTorch training via torchrun (typed H100 by default).

Launch JupyterLab on a compute node and return the SSH tunnel instructions. Never opens a tunnel itself.

Serve a model with vLLM (OpenAI-compatible API) on a full-H100 node and return tunnel instructions.

Build/update a conda environment under the project's envs/ as a CPU job (never uses /home or a GPU).

Cancel one of YOUR jobs (ownership verified first). Requires confirm=true. jobId optional only when a project scope is given (cancels the latest in that project).

Hold one of YOUR pending jobs (ownership verified). Requires confirm=true. jobId optional only with a project scope.

Release one of YOUR held jobs (ownership verified). Requires confirm=true. jobId optional only with a project scope.

Show your current Slurm queue (running/pending), optionally filtered by state or project.

Recent finished jobs via sacct, merged with local run history.

Plain-English why-pending / why-failed for a job: state + reason + efficiency (seff) + a log tail, with a practical fix. jobId optional — defaults to your most recent job (or the latest in a given project).

Fetch a job's stdout/stderr (byte-capped, restricted to its log files). jobId optional — defaults to your most recent job.

Last N lines of a job's logs plus its current state. jobId optional — defaults to your most recent job.

Make sure a conda environment exists for a project, building it automatically (PyTorch on the CUDA-12.4 wheels by default) if missing — zero manual steps. dryRun preview by default; confirm to build.

List available Lmod modules on RIS (optionally filtered).

List conda environments visible on RIS (base + project-local).

List packages in a named or path-based conda env.

Render a ready-to-edit sbatch script for any job type. Generate only — never submits.

Suggest cpus/mem/gpus/walltime/partition from a description (heuristic, offline).

Use seff/sacct to recommend right-sizing for a job or your recent runs.

Side-by-side comparison of 2+ jobs (resources, exit state, elapsed, efficiency).

Submit a chain of Python jobs with --dependency=afterok between stages. dryRun preview by default; confirm to submit the chain.

Set up the per-user worker: create the control-plane dirs under /.risbridge and submit a low-resource general-cpu daemon that submits/polls jobs for you (minimizes repeat Duo logins). dryRun preview by default.

Queue a Python job for the per-user worker to submit (so the agent need not stay connected). Builds and validates the sbatch script, then appends a request to the worker queue.

Read the status of a worker-queued run by its id.

Ask the worker to cancel a queued/submitted run (appends a cancel request).