create_agent | PolicyLayer

WHAT IT DOES

What create_agent does on Claude Code MCP - Agent Orchestration Platform

AI agents invoke create_agent to trigger actions in Claude Code MCP - Agent Orchestration Platform. 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 create_agent needs a policy

Creating a new agent involves spawning a new process, launching an iTerm2 session, and initializing an AI agent runtime — all of which constitute executing external operations with significant side effects. While technically a 'create' action, the process-spawning and agent orchestration aspects make this Execute-level.

From the tool's definition Create new Claude Code agent with comprehensive iTerm2 and process management

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_agent Rate-limited

create_agent 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": {
    "create_agent": {
      "limits": [
        {
          "counter": "create_agent_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 Code MCP - Agent Orchestration Platform, so you can run agents against it safely.

FAQ

Questions about create_agent

What does the create_agent tool do? +

Create new Claude Code agent with comprehensive iTerm2 and process management. It is categorised as a Execute tool in the Claude Code MCP - Agent Orchestration Platform MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_agent? +

Register the Claude Code MCP - Agent Orchestration Platform MCP server in PolicyLayer and add a rule for create_agent: 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 Code MCP - Agent Orchestration Platform. Nothing to install.

What risk level is create_agent? +

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

Can I rate-limit create_agent? +

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

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

create_agent is provided by the Claude Code MCP - Agent Orchestration Platform MCP server (nexus-digital-automations/claude_code_mcp_2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.