AI agents use send_message to create or update resources in ZMCPTools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ZMCPTools environment.
The tool writes/creates message data within a coordination system used for agent orchestration. This is reversible (messages can be edited or deleted), so it is Write rather than Destructive or Execute. However, in a multi-agent system, malicious messages could misdirect other agents into harmful actions, creating a moderate blast radius.
From the tool's definition Tool name is 'send_message' and description states it will 'Send message to coordination room'. This creates/modifies data (the message content in the coordination room) in a reversible manner.
Documented attack patterns abuse exactly the kind of access send_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ZMCPTools, and nothing reaches the server without passing your rules. This is the rule we recommend for send_message:
{
"version": "1",
"default": "deny",
"tools": {
"send_message": {
"limits": [
{
"counter": "send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Send message to coordination room. It is categorised as a Write tool in the ZMCPTools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ZMCPTools 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 ZMCPTools. Nothing to install.
send_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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.
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.
send_message is provided by the ZMCPTools MCP server (zachhandley/zmcptools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 70 ZMCPTools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
70 ZMCPTools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.