AI agents call prune_recovered_workers to permanently remove resources in Claude Team MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The word 'prune' strongly implies irreversible removal or cleanup of recovered worker sessions. In the context of this server, workers are Claude Code sessions with associated terminal windows and git worktrees — pruning them would likely terminate sessions and potentially remove associated resources. However, the empty description lowers confidence significantly.
From the tool's definition Tool name 'prune_recovered_workers' — 'prune' implies removal/deletion of worker sessions; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access prune_recovered_workers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Team MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for prune_recovered_workers:
{
"version": "1",
"default": "deny",
"hide": [
"prune_recovered_workers"
]
}prune_recovered_workers 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.
prune_recovered_workers. It is categorised as a Destructive tool in the Claude Team MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Team MCP Server MCP server in PolicyLayer and add a rule for prune_recovered_workers: 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 Claude Team MCP Server. Nothing to install.
prune_recovered_workers 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 prune_recovered_workers 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 prune_recovered_workers. 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.
prune_recovered_workers is provided by the Claude Team MCP Server MCP server (martian-engineering/maniple). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Team MCP Server, 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.
16 Claude Team MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.