pause_agent

Pause a running descendant child agent task. This tool only works for tasks spawned by the current task (descendants).

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-os/pause-agent.md

WHAT IT DOES

What pause_agent does on CoWork OS

AI agents invoke pause_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.

RISK

Why pause_agent is rated High

This tool controls the execution state of running agent tasks by pausing them. It triggers an external operational change (suspending agent execution), which qualifies as Execute. It is not destructive (pause is reversible), not financial, and not a simple read/write. Severity is medium because misuse could halt legitimate agent workflows, but the effect is reversible.

From the tool's definition Pause a running descendant child agent task. This tool only works for tasks spawned by the current task (descendants).

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pause_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 pause_agent, this is the rule to start with:

pause_agent Rate-limited

pause_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": {
    "pause_agent": {
      "limits": [
        {
          "counter": "pause_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every pause_agent call is checked against it from then on.

FAQ

Questions about pause_agent

What does the pause_agent tool do? +

Pause a running descendant child agent task. This tool only works for tasks spawned by the current task (descendants). 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.

How do I enforce a policy on pause_agent? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for pause_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.

What risk level is pause_agent? +

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

Can I rate-limit pause_agent? +

Yes. Add a rate_limit block to the pause_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 pause_agent completely? +

Set action: deny in the PolicyLayer policy for pause_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 pause_agent? +

pause_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.

KEEP EXPLORING

More on CoWork OS, and thousands of servers like it.

This server

All 342 CoWork OS tools → High-risk tools on this server →

Across the catalogue

pause_renders on Why Did You Render →music_pause on Apple Apps MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →