hooks_build-agents · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hooks_build-agents does on Claude Flow

AI agents invoke hooks_build-agents to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why hooks_build-agents needs a policy

This tool runs code generation and agent configuration logic, triggering external operations (agent spawning/initialization) whose effects depend on input arguments. It is Execute rather than Write because it involves code execution and hook-based automation, not merely data creation. Severity is high because misconfigured agent spawning in a multi-agent orchestration system could cascade across the swarm.

From the tool's definition Tool description states 'Generate optimized agent configurations' and references 'native Bash hooks (via Claude Code' — indicates execution of code/bash commands to build and configure agents, with effects dependent on the configuration parameters supplied.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hooks_build-agents Rate-limited

hooks_build-agents stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_build-agents": {
      "limits": [
        {
          "counter": "hooks_build-agents_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_build-agents

What does the hooks_build-agents tool do? +

Generate optimized agent configurations from pretrain data Use when native Bash hooks (via Claude Code\. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hooks_build-agents? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_build-agents: 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_build-agents? +

hooks_build-agents is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit hooks_build-agents? +

Yes. Add a rate_limit block to the hooks_build-agents 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_build-agents completely? +

Set action: deny in the PolicyLayer policy for hooks_build-agents. 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_build-agents? +

hooks_build-agents 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.