This record as markdown: /tools/io-github-homenshum-nodebench/cleanup-stale-runs.md
What cleanup_stale_runs does on Nodebench
AI agents call cleanup_stale_runs to permanently remove resources in Nodebench, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why cleanup_stale_runs is rated Critical
Cleaning up orphaned or stale runs typically involves irreversible deletion of run records and associated data. While 'cleanup' could theoretically be reversible, orphaned run cleanup is conventionally a destructive operation with no standard undo path. The description is truncated, which lowers confidence slightly, but the intent is clearly to remove stuck/orphaned data permanently.
From the tool's definition 'Clean up orphaned eval runs stuck in' — implies permanently removing/deleting stale/orphaned evaluation run data
Attacks that exploit this kind of access
The rule that runs cleanup_stale_runs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cleanup_stale_runs, this is the rule to start with:
cleanup_stale_runs is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every cleanup_stale_runs call is checked against it from then on.
Questions about cleanup_stale_runs
Clean up orphaned eval runs stuck in. It is categorised as a Destructive tool in the Nodebench MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nodebench MCP server in PolicyLayer and add a rule for cleanup_stale_runs: 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 Nodebench. Nothing to install.
cleanup_stale_runs is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cleanup_stale_runs 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 cleanup_stale_runs. 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.
cleanup_stale_runs is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue