quick_message · Iris MCP: Risk & Policy

WHAT IT DOES

What quick_message does on Iris MCP

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

WHY IT NEEDS A POLICY

Why quick_message needs a policy

This tool creates new message data in a communication system. While messaging itself is low-risk, the fire-and-forget async behavior means an AI agent could spam teams, send misleading information across codebases, or disrupt coordination without confirmation. The ability to quickly send unbounded messages to teams raises the severity to medium.

From the tool's definition Tool description states it "send[s] a message to a team" - this is a write operation that creates/transmits data. The async/fire-and-forget nature indicates it modifies state (message queue/log) without reversibility constraints typical of Execute tools.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

quick_message Rate-limited

quick_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": {
    "quick_message": {
      "limits": [
        {
          "counter": "quick_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 Iris MCP, so you can run agents against it safely.

FAQ

Questions about quick_message

What does the quick_message tool do? +

Quickly send a message to a team without waiting (async/fire-and-forget). It is categorised as a Write tool in the Iris MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on quick_message? +

Register the Iris MCP server in PolicyLayer and add a rule for quick_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 Iris MCP. Nothing to install.

What risk level is quick_message? +

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

Can I rate-limit quick_message? +

Yes. Add a rate_limit block to the quick_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 quick_message completely? +

Set action: deny in the PolicyLayer policy for quick_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 quick_message? +

quick_message is provided by the Iris MCP server (jenova-marie/iris-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.