AI agents use create_workflow to create or update resources in Srunx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Srunx environment.
This tool creates a new workflow, which is reversible data creation (workflows can be deleted or modified). It affects the SLURM job queue and computational resources, making it high severity due to potential impact on shared infrastructure, but it is Write rather than Execute because the tool itself does not run jobs—it only creates workflow definitions.
From the tool's definition Tool name 'create_workflow' indicates creation of a new workflow in a SLURM job management system. No description provided, but the name and context (sibling tools manage jobs/workflows) clearly indicate data creation.
Documented attack patterns abuse exactly the kind of access create_workflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Srunx, and nothing reaches the server without passing your rules. This is the rule we recommend for create_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"create_workflow": {
"limits": [
{
"counter": "create_workflow_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_workflow stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
create_workflow. It is categorised as a Write tool in the Srunx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Srunx MCP server in PolicyLayer and add a rule for create_workflow: 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 Srunx. Nothing to install.
create_workflow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_workflow 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 create_workflow. 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.
create_workflow is provided by the Srunx MCP server (ksterx/srunx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Srunx, 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.
14 Srunx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.