start_work · Node Dev MCP Server MCP: Risk & Policy

WHAT IT DOES

What start_work does on Node Dev MCP Server

AI agents invoke start_work to trigger actions in Node Dev MCP Server. 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_work needs a policy

This tool triggers multiple external operations: Git pull, branch creation, Git push, and dependency installation. These are Execute-class actions because they invoke shell/system commands whose side effects are not fully predictable without inspecting the remote repository state and install scripts.

From the tool's definition The tool description states it "pull[s] latest changes, create[s] and push[es] a branch, and install[s] dependencies" - these are operations that execute external commands (Git operations and npm/yarn install), whose effects depend on environment variables…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_work Rate-limited

start_work 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_work": {
      "limits": [
        {
          "counter": "start_work_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 Node Dev MCP Server, so you can run agents against it safely.

FAQ

Questions about start_work

What does the start_work tool do? +

Set remote URL from env, pull latest changes, create and push a branch, and install dependencies. It is categorised as a Execute tool in the Node Dev MCP Server 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_work? +

Register the Node Dev MCP Server MCP server in PolicyLayer and add a rule for start_work: 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 Node Dev MCP Server. Nothing to install.

What risk level is start_work? +

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

Can I rate-limit start_work? +

Yes. Add a rate_limit block to the start_work 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_work completely? +

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

start_work is provided by the Node Dev MCP Server MCP server (liamcarver/node-dev-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.