agent_communication_send_message

WHAT IT DOES

What agent_communication_send_message does on Agent Communication MCP Server

AI agents use agent_communication_send_message to create or update resources in Agent Communication MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Communication MCP Server environment.

WHY IT NEEDS A POLICY

Why agent_communication_send_message needs a policy

The tool creates new message records in a room-based communication system. While messages can typically be edited or deleted later, the primary action is creation of data (Write category). Severity is low because message posting has minimal blast radius—it affects only communication within rooms and does not cause destructive changes, execute arbitrary operations, or move financial resources.

From the tool's definition Tool name 'agent_communication_send_message' and description 'Send a message to a room' indicate creation of new message data in a collaborative channel. This is a reversible write operation analogous to posting in Slack.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_communication_send_message Rate-limited

agent_communication_send_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": {
    "agent_communication_send_message": {
      "limits": [
        {
          "counter": "agent_communication_send_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 Communication MCP Server, so you can run agents against it safely.

FAQ

Questions about agent_communication_send_message

What does the agent_communication_send_message tool do? +

Send a message to a room. It is categorised as a Write tool in the Agent Communication MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on agent_communication_send_message? +

Register the Agent Communication MCP Server MCP server in PolicyLayer and add a rule for agent_communication_send_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 Agent Communication MCP Server. Nothing to install.

What risk level is agent_communication_send_message? +

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

Can I rate-limit agent_communication_send_message? +

Yes. Add a rate_limit block to the agent_communication_send_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 agent_communication_send_message completely? +

Set action: deny in the PolicyLayer policy for agent_communication_send_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 agent_communication_send_message? +

agent_communication_send_message is provided by the Agent Communication MCP Server MCP server (mkxultra/agent-communication-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.