Detect, classify, and clean up artifacts generated by AI coding agents (e.g., TODO.md, PLAN.md, agent markers, temporary files). Supports scan, clean, and archive operations with configurable patterns.
AI agents call cleanup_agent_artifacts to permanently remove resources in Documcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly supports a 'clean' operation that removes files from the repository. Deleting or purging files (TODO.md, PLAN.md, temporary files, agent markers) is irreversible unless backed up. Even 'archive' may overwrite existing data. The most severe applicable category is Destructive. Severity is high because misuse could silently delete important project files that happen to match the configured patterns.
From the tool's definition 'clean up artifacts', 'clean, and archive operations' — the 'clean' operation permanently removes files from the repository
Documented attack patterns abuse exactly the kind of access cleanup_agent_artifacts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Documcp, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanup_agent_artifacts:
{
"version": "1",
"default": "deny",
"hide": [
"cleanup_agent_artifacts"
]
}cleanup_agent_artifacts disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Detect, classify, and clean up artifacts generated by AI coding agents (e.g., TODO.md, PLAN.md, agent markers, temporary files). Supports scan, clean, and archive operations with configurable patterns. It is categorised as a Destructive tool in the Documcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Docu MCP server in PolicyLayer and add a rule for cleanup_agent_artifacts: 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 Documcp. Nothing to install.
cleanup_agent_artifacts 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_agent_artifacts 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_agent_artifacts. 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_agent_artifacts is provided by the Docu MCP server (tosin2013/documcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Documcp, 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.
52 Documcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.