Critical Risk →

pf_defederate

Defederate from a remote domain (block + purge cached content + sever follows). QUEUED — requires operator confirmation.

How to control pf_defederate ↓

What pf_defederate does on Crow

AI agents call pf_defederate to permanently remove resources in Crow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why pf_defederate needs a policy

Although the action is queued and requires operator confirmation (a safeguard), the tool's core function is to irreversibly delete cached content and terminate federation relationships. This matches Destructive category (actions that cannot be undone). The context of a federated system means defederation affects multiple parties and persistent state.

From the tool's definition Tool description explicitly states 'block + purge cached content + sever follows' — these are irreversible actions. 'Purge' indicates deletion of data that cannot be restored, and 'sever follows' permanently breaks relationships.

Documented attack patterns abuse exactly the kind of access pf_defederate gives an agent:

How to control pf_defederate

PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for pf_defederate:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "pf_defederate"
  ]
}

pf_defederate disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Crow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about pf_defederate

What does the pf_defederate tool do? +

Defederate from a remote domain (block + purge cached content + sever follows). QUEUED — requires operator confirmation. It is categorised as a Destructive tool in the Crow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on pf_defederate? +

Register the Crow MCP server in PolicyLayer and add a rule for pf_defederate: 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 Crow. Nothing to install.

What risk level is pf_defederate? +

pf_defederate is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit pf_defederate? +

Yes. Add a rate_limit block to the pf_defederate 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.

How do I block pf_defederate completely? +

Set action: deny in the PolicyLayer policy for pf_defederate. 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.

What MCP server provides pf_defederate? +

pf_defederate is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crow tool call.

Start from Crow, 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.

576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.