orchestrate_agents
Spawn multiple sub-agents in parallel and wait for all of them to complete.
This record as markdown: /tools/cowork-os/orchestrate-agents.md
What orchestrate_agents does on CoWork OS
AI agents invoke orchestrate_agents 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 orchestrate_agents is rated High
This tool spawns and executes multiple sub-agents in parallel. The effects are entirely dependent on what those agents do — they could read, write, delete, or trigger external operations. Spawning arbitrary agents represents a broad execution surface with high blast radius if misused, as a single call could fan out into many consequential actions across systems.
From the tool's definition Spawn multiple sub-agents in parallel and wait for all of them to complete
Attacks that exploit this kind of access
The rule that runs orchestrate_agents 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 orchestrate_agents, this is the rule to start with:
orchestrate_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.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every orchestrate_agents call is checked against it from then on.
Questions about orchestrate_agents
Spawn multiple sub-agents in parallel and wait for all of them to complete. 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 orchestrate_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 CoWork OS. Nothing to install.
orchestrate_agents 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 orchestrate_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.
Set action: deny in the PolicyLayer policy for orchestrate_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.
orchestrate_agents 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