daa_agent_create · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What daa_agent_create does on Claude Flow

AI agents invoke daa_agent_create 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 daa_agent_create needs a policy

This tool spawns autonomous agents that operate independently, adapt behavior dynamically, and interact with a broader swarm. Creating autonomous agents that execute tasks and share knowledge across a distributed system is an Execute-category action with high severity — a misused or misdirected autonomous agent could trigger cascading unintended operations across the swarm at scale.

From the tool's definition "Create a decentralized autonomous agent" that "adapt their cognitive pattern" and "share knowledge across the swarm"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

daa_agent_create Rate-limited

daa_agent_create 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": {
    "daa_agent_create": {
      "limits": [
        {
          "counter": "daa_agent_create_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 daa_agent_create

What does the daa_agent_create tool do? +

Create a decentralized autonomous agent Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one-shot agents, native Task is fine. 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 daa_agent_create? +

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

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

Can I rate-limit daa_agent_create? +

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

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

daa_agent_create 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.