spawn_agents · Agent Link MCP: Risk & Policy

WHAT IT DOES

What spawn_agents does on Agent Link

AI agents invoke spawn_agents 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_agents needs a policy

Spawning multiple AI agents triggers external process execution with potentially unbounded side effects depending on the tasks assigned. Each agent could perform reads, writes, or even destructive actions. The blast radius is high because an AI agent could misuse this to launch many autonomous agents performing harmful or unintended operations at scale.

From the tool's definition 'Spawn multiple AI agents in parallel' — spawns and runs external agent CLI processes whose effects depend entirely on the arguments passed

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spawn_agents Rate-limited

spawn_agents 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_agents": {
      "limits": [
        {
          "counter": "spawn_agents_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_agents

What does the spawn_agents tool do? +

Spawn multiple AI agents in parallel. Each agent runs independently and results are returned together. Great for getting multiple opinions, parallel code reviews, or distributing subtasks. 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_agents? +

Register the Agent Link MCP server in PolicyLayer and add a rule for spawn_agents: 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_agents? +

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

Can I rate-limit spawn_agents? +

Yes. Add a rate_limit block to the spawn_agents 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_agents completely? +

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

spawn_agents 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.