log · TDD- MCP: Risk & Policy

WHAT IT DOES

What log does on TDD-MCP

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

WHY IT NEEDS A POLICY

Why log needs a policy

The tool creates/appends data (log entries) to session state in a reversible manner. It is not destructive because log entries can be cleared or overwritten; it does not execute arbitrary code or commands, and it has no financial implications.

From the tool's definition Tool description states it 'Add[s] a log entry to the current session' — a create operation that modifies session state by appending a record.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log Rate-limited

log 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": {
      "limits": [
        {
          "counter": "log_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 TDD-MCP, so you can run agents against it safely.

FAQ

Questions about log

What does the log tool do? +

Add a log entry to the current session without affecting workflow state. It is categorised as a Write tool in the TDD-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 log? +

Register the TDD- MCP server in PolicyLayer and add a rule for log: 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 TDD-MCP. Nothing to install.

What risk level is log? +

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

Can I rate-limit log? +

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

Set action: deny in the PolicyLayer policy for log. 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? +

log is provided by the TDD- MCP server (tinmancoding/tdd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.