pf_follow
Follow an account by handle (@user@domain) or local account ID. Rate-limited: 30/hour.
This record as markdown: /tools/kh0pper-crow/pf-follow.md
What pf_follow does on Crow
AI agents use pf_follow 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.
Why pf_follow is rated Medium
Following an account creates a persistent social relationship on the platform. This is a reversible write action (can be unfollowed), but misuse could cause unwanted follows at scale (rate-limited to 30/hour suggests potential for abuse). No data is deleted or money moved.
From the tool's definition Follow an account by handle (@user@domain) or local account ID
Attacks that exploit this kind of access
The rule that runs pf_follow safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pf_follow, this is the rule to start with:
pf_follow 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every pf_follow call is checked against it from then on.
Questions about pf_follow
Follow an account by handle (@user@domain) or local account ID. Rate-limited: 30/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_follow: 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_follow 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_follow 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_follow. 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_follow 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.
More on Crow, and thousands of servers like it.
This server
Across the catalogue