start_watcher · Python Codebase Analysis RAG System MCP

WHAT IT DOES

What start_watcher does on Python Codebase Analysis RAG System

AI agents invoke start_watcher to trigger actions in Python Codebase Analysis RAG System. 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_watcher needs a policy

Starting a file watcher is an active operation that triggers external monitoring functionality and maintains state. While not destructive, it goes beyond read-only queries and creates ongoing background activity. The tool could be misused to monitor sensitive directories or drain resources through excessive watching.

From the tool's definition Tool description states it 'Starts a file watcher for the specified codebase directory' — actively initiates a background process to monitor file system changes, which is an external operation with side effects that depend on the specified directory argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_watcher Rate-limited

start_watcher 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_watcher": {
      "limits": [
        {
          "counter": "start_watcher_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 Python Codebase Analysis RAG System, so you can run agents against it safely.

FAQ

Questions about start_watcher

What does the start_watcher tool do? +

Starts a file watcher for the specified codebase directory. It is categorised as a Execute tool in the Python Codebase Analysis RAG System 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_watcher? +

Register the Python Codebase Analysis RAG System MCP server in PolicyLayer and add a rule for start_watcher: 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 Python Codebase Analysis RAG System. Nothing to install.

What risk level is start_watcher? +

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

Can I rate-limit start_watcher? +

Yes. Add a rate_limit block to the start_watcher 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_watcher completely? +

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

start_watcher is provided by the Python Codebase Analysis RAG System MCP server (shervinemp/codebasemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.