annotated_message · MCP Everything MCP: Risk & Policy

WHAT IT DOES

What annotated_message does on MCP Everything

AI agents call annotated_message as a supporting operation in MCP Everything workflows.

WHY IT NEEDS A POLICY

Why annotated_message needs a policy

The description is empty, providing no information about what this tool does. The name 'annotated_message' suggests it may display or return a message with annotations, which would likely be a Read or Write operation, but without any description, confidence is very low. Given the server is a test server and sibling tools are mostly benign test utilities (echo, add, get_tiny_image), this is likely a low-risk tool.

From the tool's definition Tool name is 'annotated_message' and description is empty or uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

annotated_message Rate-limited

annotated_message gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "annotated_message": {
      "limits": [
        {
          "counter": "annotated_message_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Everything, so you can run agents against it safely.

FAQ

Questions about annotated_message

What does the annotated_message tool do? +

annotated_message. It is categorised as a Other tool in the MCP Everything MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on annotated_message? +

Register the MCP Everything MCP server in PolicyLayer and add a rule for annotated_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 MCP Everything. Nothing to install.

What risk level is annotated_message? +

annotated_message is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit annotated_message? +

Yes. Add a rate_limit block to the annotated_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 annotated_message completely? +

Set action: deny in the PolicyLayer policy for annotated_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 annotated_message? +

annotated_message is provided by the MCP Everything MCP server (s2005/mcp-everything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.