log_message · Small MCP: Risk & Policy

WHAT IT DOES

What log_message does on Small

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

WHY IT NEEDS A POLICY

Why log_message needs a policy

Logging is a write operation that records data reversibly. The tool creates a log entry and echoes the message back, which are side effects but not destructive, executable in a dangerous sense, or financial. The blast radius of misuse is minimal—at worst, logs could be polluted with noise or sensitive information could be logged, but the operation is inherently reversible and low-impact.

From the tool's definition Tool description states 'Log a message through the MCP context and echo it back', indicating it writes/records data (logging) but does not delete, execute external code, or cause destructive effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_message Rate-limited

log_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": {
    "log_message": {
      "limits": [
        {
          "counter": "log_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 Small, so you can run agents against it safely.

FAQ

Questions about log_message

What does the log_message tool do? +

Log a message through the MCP context and echo it back. It is categorised as a Write tool in the Small MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on log_message? +

Register the Small MCP server in PolicyLayer and add a rule for log_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 Small. Nothing to install.

What risk level is log_message? +

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

Can I rate-limit log_message? +

Yes. Add a rate_limit block to the log_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 log_message completely? +

Set action: deny in the PolicyLayer policy for log_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 log_message? +

log_message is provided by the Small MCP server (nishant-iit/smallmp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.