spawn_agent · Agent Link MCP: Risk & Policy

WHAT IT DOES

What spawn_agent does on Agent Link

AI agents invoke spawn_agent to trigger actions in Agent Link. 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_agent needs a policy

Spawning an AI agent triggers an external process/operation with unpredictable side effects depending on what task the agent is instructed to perform. This is an Execute-category action with high severity because a misused agent could perform destructive, financial, or otherwise harmful operations on behalf of the caller. The blast radius is high since the spawned agent may itself have broad capabilities.

From the tool's definition 'Spawn an AI agent to work on a task' — launches an external agent CLI process whose effects depend entirely on the task arguments provided

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spawn_agent Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "spawn_agent": {
      "limits": [
        {
          "counter": "spawn_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 Agent Link, so you can run agents against it safely.

FAQ

Questions about spawn_agent

What does the spawn_agent tool do? +

Spawn an AI agent to work on a task. Returns a question if the agent needs clarification, or a result when done. It is categorised as a Execute tool in the Agent Link 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 Agent Link 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 Agent Link. 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 Agent Link MCP server (mikusnuz/agent-link-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.