hooks_init · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hooks_init does on Claude Flow

AI agents use hooks_init to create or update resources in Claude Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.

WHY IT NEEDS A POLICY

Why hooks_init needs a policy

This tool creates or modifies configuration files (specifically .claude/settings.json) to set up hooks in a project. It is a Write operation as it creates/initializes configuration. The severity is medium because misconfigured hooks could affect project behavior, but it's reversible. Confidence is slightly reduced due to the truncated description ('via Claude Code\') which may hide additional behavior.

From the tool's definition Initialize hooks in project with .claude/settings.json

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hooks_init Rate-limited

hooks_init 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hooks_init": {
      "limits": [
        {
          "counter": "hooks_init_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about hooks_init

What does the hooks_init tool do? +

Initialize hooks in project with .claude/settings.json Use when native Bash hooks (via Claude Code\. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on hooks_init? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_init: 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 Flow. Nothing to install.

What risk level is hooks_init? +

hooks_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit hooks_init? +

Yes. Add a rate_limit block to the hooks_init 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 hooks_init completely? +

Set action: deny in the PolicyLayer policy for hooks_init. 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 hooks_init? +

hooks_init is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.