send_message · Agent-Comm-Hub MCP: Risk & Policy

Q: How do I enforce a policy on send_message?

Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for 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-Comm-Hub. Nothing to install.

Q: What risk level is send_message?

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

Q: Can I rate-limit send_message?

Yes. Add a rate_limit block to the 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.

Q: How do I block send_message completely?

Set action: deny in the PolicyLayer policy for 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.

Q: What MCP server provides send_message?

send_message is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

WHAT IT DOES

What send_message does on Agent-Comm-Hub

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

WHY IT NEEDS A POLICY

Why send_message needs a policy

This tool creates new messages in the system's persistent storage. While not destructive (messages can be read/managed), it modifies shared state that other agents depend on.

From the tool's definition Tool sends messages between agents with persistence: '向另一个 Agent 发送即时消息' (send instant messages to another Agent), with offline storage and automatic redelivery ('离线时持久化存储，上线后自动补发'). Creates/modifies data (messages) in a shared communication system.

Attacks that exploit this kind of access

Questions about send_message

What does the send_message tool do? +

向另一个 Agent 发送即时消息。对方在线时实时送达（<50ms），离线时持久化存储，上线后自动补发。. It is categorised as a Write tool in the Agent-Comm-Hub 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_message? +

Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for 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-Comm-Hub. Nothing to install.

What risk level is send_message? +

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

Can I rate-limit send_message? +

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

Set action: deny in the PolicyLayer policy for 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 send_message? +

send_message is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.