collective-decide · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What collective-decide does on Claude Flow

AI agents invoke collective-decide 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 collective-decide needs a policy

This tool actively invokes a collective decision-making operation across a swarm of agents. While 'decide' sounds passive, it triggers execution of agent coordination logic whose effects depend entirely on the decision context and what downstream actions the agents may take as a result.

From the tool's definition "Request collective decision from agents" — triggers coordinated multi-agent decision-making process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

collective-decide Rate-limited

collective-decide 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": {
    "collective-decide": {
      "limits": [
        {
          "counter": "collective-decide_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 collective-decide

What does the collective-decide tool do? +

Request collective decision from agents. 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 collective-decide? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for collective-decide: 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 collective-decide? +

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

Can I rate-limit collective-decide? +

Yes. Add a rate_limit block to the collective-decide 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 collective-decide completely? +

Set action: deny in the PolicyLayer policy for collective-decide. 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 collective-decide? +

collective-decide 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.