Best for
- Scientific computing users who need Slurm cluster management.
- AI agent developers who want to automate HPC job lifecycles.
C
CLIO Slurm
Community
MCP server for Slurm workload management and HPC job scheduling
- Category
- Other #42 of 230
- Stars
- ★ 30 Popular
- Transport
- stdio (local process)
- Runtime
- Python 3.10+
- Credentials
- No credential needed
- License
- BSD-3-Clause
- Last commit
- Tools
- 5
64FMRS · C
CLIO Slurm offers a clean job management interface for Slurm clusters. The tool naming and functionality are clear, and the confirmation mechanism reduces the risk of accidental destructive actions. As part of the IoWarp scientific computing ecosystem, it is aimed at HPC administrators and researchers who want to leverage AI in their workflows. As a subcomponent, its documentation relies heavily on the overall CLIO Kit, which may complicate standalone use when deployed as a single server.
Strongest · Setup experience 14/20 Weakest · Reliability 10/20
Why each score
- Reliability 10/20
- Manifest declares 5 coherent tools (submit/list/describe/cluster/cancel) with a well-designed double-confirmation for cancellation; README claims CI, codecov, mypy, ruff and machine-readable user contracts for SLURM v3 with SHA-256 digests, but no actual test files or CI run evidence for this specific server is supplied, so tool behavior cannot be statically verified; version inconsistencies (manifest 3.0.0/package 2.10.6 vs README example 2.4.3) risk mismatched installs, hence deductions.
- Security and permissions 14/20
- The cancel tool requires confirm_job_id to exactly repeat job_id before scancel — good destructive-operation guard. However slurm_submit can submit arbitrary jobs (resource consumption on HPC) with no disclosed quota, allowlist, or script-path restrictions; stdio local transport means no network exposure, no malware or credential-leak indicators; but required Slurm privileges/data boundaries are undocumented. No red-line violation.
- Maintenance 14/20
- BSD-3-Clause license, not archived, 39 open issues, CI/codecov/ruff/mypy/pip-audit badges, NSF/IIT institutional backing, Zulip support channel, and a versioned contract system (SLURM 3.0). However 26 stars and no evidence of issue-response latency; README badge counts inconsistently claim 22/23/24 servers, indicating doc drift; slight deduction.
- Documentation 12/20
- Install instructions, per-client configs (Cursor/Claude Code/VS Code/Claude Desktop) and a troubleshooting section are present; but no server-specific parameter/output/limit docs for the Slurm tools (tail bounds, state formats), and README usage examples cite tool names (submit_slurm_job, check_job_status, get_job_output) that do not match the manifest's slurm_submit/slurm_list/slurm_describe — stale documentation is a clear deduction.
- Setup experience 14/20
- One-command uv tool install, concrete claude mcp add and JSON client examples, zero-network stdio transport, and a documented slurm entrypoint; but the manifest pins clio-kit 2.10.6 while README examples use 2.4.3, creating version confusion; plus prerequisites (uv, a Slurm environment) and no static execution verification keep it below 15.
Static review · not runListed 2026-09-08
Read the FMRS scoring method →Fit and risk
What it can accessRuns commands or codeUses the network
Not for
- Systems that do not use Slurm as their scheduler (e.g., PBS, LSF).
- Users who require a graphical interface or interactive terminal sessions.
- Users who prefer manually scripted Slurm jobs over AI-driven interactions.
Required permissions
- Requires access to Slurm commands (e.g., `sbatch`, `squeue`, `scontrol`, `scancel`, `sinfo`).
- Depends on execution environment: listing jobs typically requires only user-level permissions; canceling or submitting jobs may require additional authorization.
- May require access to the filesystem where job output files are stored.
Risks and side effects
- The `slurm_cancel` tool is destructive—it cancels jobs, potentially losing progress. The built-in `confirm_job_id` mechanism helps prevent accidental cancellation, but misuse can still have impact.
- Resource submission can consume significant cluster resources, potentially affecting other users.
- Sensitive information may be exposed through job descriptions or outputs.
- Misconfiguration in a shared HPC environment could lead to permission issues.
Setup
Before you start
Runtime：Python 3.10+
- Ensure Python 3.10+ and uv are installed.
- Install CLIO Kit with
uv tool install 'clio-kit==2.4.3'(or latest version). - Update PATH:
uv tool update-shell. - Configure the server in your MCP client, for example:
{"mcpServers": {"slurm-mcp": {"command": "clio-kit", "args": ["mcp-server", "slurm"]}}}
- Verify that Slurm commands (e.g.,
sinfo,squeue,sbatch,scancel) are available in your environment.
Check that it works
After installation, the client's tool list should show slurm_submit, slurm_list, slurm_describe, slurm_cluster, and slurm_cancel; alternatively run clio-kit mcp-server slurm to confirm it starts without errors.
Troubleshooting
- Check that Slurm commands are available: run `which sbatch`, `which squeue`.
- Ensure `clio-kit` is correctly installed and the version is compatible.
- Look at server logs for detailed error messages.
- Verify that you have sufficient Slurm user permissions to perform the intended operations (e.g., canceling jobs).
Things to try
Once connected, you can ask your AI assistant things like:
- Submit simulation.py to Slurm with 32 cores, 64GB memory, and a 24-hour runtime.
- List my currently RUNNING Slurm jobs.
- Describe Slurm job 12345 including its lifecycle state and stdout/stderr tails.
- Show me the Slurm partitions and queue records for this cluster.
Tools 5
slurm_submit writes
Submit one Slurm job or array and return its scheduler-native job ID. Set array only for an array submission.
slurm_list read-only
List a bounded number of Slurm jobs with optional user, state, and partition filters. Returns native IDs and explicit truncation state.
slurm_describe read-only
Describe one scheduler-native Slurm job: lifecycle state, terminality, scheduler properties, and optional bounded stdout/stderr tails.
slurm_cluster read-only
Inspect bounded Slurm partition and queue records in one snapshot. Node details are excluded by default and bounded when requested.
slurm_cancel destructive
Request destructive cancellation of one Slurm job. confirm_job_id must exactly repeat job_id; omission or mismatch is rejected without calling scancel.
No matching tools
Use cases
Submit simulation jobs to Slurm via natural language, e.g., 'Submit simulation.py to Slurm with 32 cores'.
Monitor job status and retrieve output.
Query cluster partition and queue information.
Supported clients
Claude Desktop
Listed from the project's documentation, not tested by this site.
Overview
CLIO Slurm is a Model Context Protocol (MCP) server that provides AI agents with an interface to the Slurm workload manager. It supports submitting jobs (including job arrays), listing and describing jobs, inspecting cluster partition information, and canceling jobs. The server runs over stdio via the clio-kit package using the command clio-kit mcp-server slurm. It is part of the CLIO Kit toolset from the IoWarp platform, developed by researchers at Illinois Institute of Technology with NSF support. This server is useful for agents that need to automate Slurm job management in scientific workflows.
Similar servers
Hevy MCP
77 · B
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl MCP Server
75 · B
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
BioMCP
75 · B
One binary. One grammar. Evidence from the biomedical sources you already trust.
Compartment
75 · B
Encrypted, fully offline long-term memory for AI agents
More servers from this repository
Source revision 93e41d70d6c2 Data synced 2026-10-19 Read the FMRS scoring method