hooks_notify · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hooks_notify does on Claude Flow

AI agents use hooks_notify 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_notify needs a policy

The tool sends notifications to other agents, which is a write/trigger action with side effects on other running agents. It does not appear to execute arbitrary code or delete data, but cross-agent messaging in a hive-mind orchestration system could have meaningful blast radius if misused (e.g., flooding agents or sending malicious signals). Truncated description reduces confidence.

From the tool's definition 'Send cross-agent notification' — triggers a notification event across agents; description is truncated ('via Claude Code\') limiting full assessment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hooks_notify Rate-limited

hooks_notify 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_notify": {
      "limits": [
        {
          "counter": "hooks_notify_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_notify

What does the hooks_notify tool do? +

Send cross-agent notification 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_notify? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_notify: 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_notify? +

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

Can I rate-limit hooks_notify? +

Yes. Add a rate_limit block to the hooks_notify 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_notify completely? +

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

hooks_notify 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.