spawn_sub_agent · Qontinui MCP Server MCP: Risk & Policy

WHAT IT DOES

What spawn_sub_agent does on Qontinui MCP Server

AI agents invoke spawn_sub_agent to trigger actions in Qontinui MCP Server. 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 spawn_sub_agent needs a policy

This tool spawns an autonomous sub-agent that executes arbitrary tasks with scoped tools. It triggers external operations whose effects entirely depend on the arguments passed (the task and tools given to the sub-agent). Since the sub-agent runs autonomously and can presumably invoke any of the sibling tools (including destructive ones like delete_test or execute workflows), the blast radius is high.

From the tool's definition 'Spawn a sub-agent with a specific task and optionally scoped tools. The sub-agent runs autonomously and returns when complete.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spawn_sub_agent Rate-limited

spawn_sub_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": {
    "spawn_sub_agent": {
      "limits": [
        {
          "counter": "spawn_sub_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 Qontinui MCP Server, so you can run agents against it safely.

FAQ

Questions about spawn_sub_agent

What does the spawn_sub_agent tool do? +

Spawn a sub-agent with a specific task and optionally scoped tools. The sub-agent runs autonomously and returns when complete. Use this for complex tasks that benefit from hierarchical decomposition. It is categorised as a Execute tool in the Qontinui MCP Server 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_sub_agent? +

Register the Qontinui MCP Server MCP server in PolicyLayer and add a rule for spawn_sub_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 Qontinui MCP Server. Nothing to install.

What risk level is spawn_sub_agent? +

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

Can I rate-limit spawn_sub_agent? +

Yes. Add a rate_limit block to the spawn_sub_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_sub_agent completely? +

Set action: deny in the PolicyLayer policy for spawn_sub_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_sub_agent? +

spawn_sub_agent is provided by the Qontinui MCP Server MCP server (qontinui/qontinui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.