send_agent_message

Send a follow-up message to a descendant child agent task. Use this to clarify instructions, provide missing

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

Medium RISK CLASS

Category Write

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/send-agent-message.md

WHAT IT DOES

What send_agent_message does on CoWork OS

AI agents use send_agent_message to create or update resources in CoWork OS, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CoWork OS environment.

RISK

Why send_agent_message is rated Medium

This tool creates new message data within an agent communication system. While the action is reversible (messages can be deleted or modified later), it affects the state of agent tasks and their instructions. It does not execute external code, delete data irreversibly, or involve financial transactions.

From the tool's definition The tool 'send_agent_message' allows sending a follow-up message to a child agent task to clarify instructions or provide information.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

send_agent_message Rate-limited

send_agent_message stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_agent_message": {
      "limits": [
        {
          "counter": "send_agent_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 send_agent_message call is checked against it from then on.

FAQ

Questions about send_agent_message

What does the send_agent_message tool do? +

Send a follow-up message to a descendant child agent task. Use this to clarify instructions, provide missing. It is categorised as a Write tool in the CoWork OS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_agent_message? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for send_agent_message: 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 send_agent_message? +

send_agent_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_agent_message? +

Yes. Add a rate_limit block to the send_agent_message 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 send_agent_message completely? +

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

send_agent_message 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 →

Across the catalogue

sms_send on Twilio SMS MCP Server →send-draft on Meme MCP Server →team_manager_kill_agent on Team Manager MCP →mail_send_draft on Apple Apps MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →