Show recently completed, failed, or cancelled SLURM jobs.
AI agents call job_history to retrieve information from Tacc Mcp Bio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays past job execution records from a SLURM cluster. It retrieves information about job states without creating, modifying, deleting, or executing any operations. The blast radius is minimal—an AI agent misusing this tool could only view job history, not affect running jobs or cluster state. This is a straightforward read operation typical of monitoring and auditing tools.
From the tool's definition Tool name 'job_history' and description 'Show recently completed, failed, or cancelled SLURM jobs' indicates retrieval of historical job status data with no modification or side effects.
Attacks that exploit this kind of access
Show recently completed, failed, or cancelled SLURM jobs. It is categorised as a Read tool in the Tacc Mcp Bio MCP Server, which means it retrieves data without modifying state.
Register the Tacc Mcp Bio MCP server in PolicyLayer and add a rule for job_history: 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 Tacc Mcp Bio. Nothing to install.
job_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the job_history 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 job_history. 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.
job_history is provided by the Tacc Mcp Bio MCP server (narasimhan-lab/tacc-mcp-bio). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →