spawn_agent
Spawn a new agent (sub-task) to work on a specific task independently. Use this to delegate work,
This record as markdown: /tools/cowork-os/spawn-agent.md
What spawn_agent does on CoWork OS
AI agents invoke spawn_agent to trigger actions in CoWork OS. 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 spawn_agent is rated High
This tool creates and launches a new autonomous agent to perform tasks independently. Spawning agents that can execute arbitrary sub-tasks represents significant execution risk — a misused or malicious invocation could trigger a cascade of automated actions across the system, amplifying blast radius substantially.
From the tool's definition 'Spawn a new agent (sub-task) to work on a specific task independently' and 'delegate work'
Attacks that exploit this kind of access
The rule that runs spawn_agent safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For spawn_agent, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every spawn_agent call is checked against it from then on.
Questions about spawn_agent
Spawn a new agent (sub-task) to work on a specific task independently. Use this to delegate work,. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS 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 CoWork OS. Nothing to install.
spawn_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
spawn_agent is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue