spawn_agent

THE RISK

High Risk

This tool creates and launches an autonomous AI agent with unrestricted tool access. An AI agent with 'complete tool access' on a platform that includes browser automation, file operations, code execution, and destructive/financial tools represents an extreme blast radius.

From the tool's definition Spawn fully autonomous Claude agent with complete tool access

Documented attack patterns abuse exactly the kind of access spawn_agent gives an agent:

HOW TO CONTROL SPAWN_AGENT

PolicyLayer is an MCP gateway — it sits between your AI agents and ZMCPTools, and nothing reaches the server without passing your rules. This is the rule we recommend for spawn_agent:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "spawn_agent": {
      "limits": [
        {
          "counter": "spawn_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

spawn_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.

Create a free account and register ZMCPTools — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More ZMCPTools tools

Destructive cancel_scrape_job Cancel an active or pending scraping job Destructive delete_all_website_pages Delete all pages for a website (useful for clean slate before re-scraping) Destructive delete_execution_plan Delete an execution plan by ID Destructive delete_pages_by_ids Delete specific pages by their IDs Destructive delete_pages_by_pattern Delete website pages matching URL patterns (useful for cleaning up version URLs, static as Destructive delete_room Permanently delete a communication room and all its messages Destructive force_unlock_job Force unlock a stuck scraping job - useful for debugging and recovery Destructive remove_file_analysis Remove analysis data for a deleted file from the TreeSummary system

All 70 ZMCPTools tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in ZMCPTools → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the spawn_agent tool do? +

Spawn fully autonomous Claude agent with complete tool access. It is categorised as a Execute tool in the ZMCPTools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on spawn_agent? +

Register the ZMCPTools MCP server in PolicyLayer and add a rule for spawn_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 ZMCPTools. Nothing to install.

What risk level is spawn_agent? +

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

Can I rate-limit spawn_agent? +

Yes. Add a rate_limit block to the spawn_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 spawn_agent completely? +

Set action: deny in the PolicyLayer policy for spawn_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 spawn_agent? +

spawn_agent is provided by the ZMCPTools MCP server (zachhandley/zmcptools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ZMCPTools tool call.

Deterministic rules across all 70 ZMCPTools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN ZMCPTOOLS →

Free to start. No card required.

70 ZMCPTools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT SPAWN_AGENT ON ZMCPTOOLS DOES

// THE RISK

// HOW TO CONTROL SPAWN_AGENT

// EXPLORE