AI agents invoke submit_slurm_job to trigger actions in slurm_MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Submitting a Slurm job causes external code/commands to execute on HPC cluster nodes, consuming compute resources and potentially running arbitrary scripts. This is an Execute-category action. The description is empty, so the inference is based on the tool name and server description.
From the tool's definition Tool name 'submit_slurm_job' and server context: 'Enables interaction with Slurm HPC clusters via SSH, allowing job submission' — submitting a job triggers execution of arbitrary workloads on HPC cluster resources.
Documented attack patterns abuse exactly the kind of access submit_slurm_job gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and slurm_MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for submit_slurm_job:
{
"version": "1",
"default": "deny",
"tools": {
"submit_slurm_job": {
"limits": [
{
"counter": "submit_slurm_job_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}submit_slurm_job stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
submit_slurm_job. It is categorised as a Execute tool in the slurm_MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the slurm_ MCP server in PolicyLayer and add a rule for submit_slurm_job: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches slurm_MCP. Nothing to install.
submit_slurm_job is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the submit_slurm_job rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for submit_slurm_job. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
submit_slurm_job is provided by the slurm_ MCP server (pengc0066-star/slurm_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from slurm_MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 slurm_MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.