Block an account system-wide (the authenticated user no longer sees their posts). Rate-limited: 5/hour.
AI agents use pf_block_user to create or update resources in Crow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
Blocking a user is a reversible write action that modifies the authenticated user's account state (block list). It does not delete data or execute code, and it can be undone by unblocking. The blast radius is medium as it affects social interactions and content visibility but is not irreversible.
From the tool's definition Block an account system-wide (the authenticated user no longer sees their posts)
Documented attack patterns abuse exactly the kind of access pf_block_user gives an agent:
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_block_user:
{
"version": "1",
"default": "deny",
"tools": {
"pf_block_user": {
"limits": [
{
"counter": "pf_block_user_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} pf_block_user stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Block an account system-wide (the authenticated user no longer sees their posts). Rate-limited: 5/hour. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for pf_block_user: 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.
pf_block_user is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pf_block_user 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 pf_block_user. 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.
pf_block_user 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.
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.