start_tracking · Early MCP: Risk & Policy

WHAT IT DOES

What start_tracking does on Early MCP

AI agents invoke start_tracking to trigger actions in Early MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_tracking needs a policy

This tool executes an operation that changes system state (starts a timer) rather than merely reading data or creating reversible records. While not destructive or financial, it represents Execute category as it triggers external action with argument-dependent effects.

From the tool's definition Tool description states 'Start tracking time for an activity' which initiates an external operation (timer start) with side effects that depend on which activity argument is provided. This is an action that triggers a real-world operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_tracking Rate-limited

start_tracking stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_tracking": {
      "limits": [
        {
          "counter": "start_tracking_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about start_tracking

What does the start_tracking tool do? +

Start tracking time for an activity. It is categorised as a Execute tool in the Early MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_tracking? +

Register the Early MCP server in PolicyLayer and add a rule for start_tracking: 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 Early MCP. Nothing to install.

What risk level is start_tracking? +

start_tracking is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_tracking? +

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

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

start_tracking is provided by the Early MCP server (sakebomb/early_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.