start_browser · Nav MCP: Risk & Policy

WHAT IT DOES

What start_browser does on Navmcp

AI agents invoke start_browser to trigger actions in Navmcp. 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_browser needs a policy

Starting a browser is an Execute action because it initiates an external process and enables subsequent automated interactions. While starting a browser alone is not destructive or financial, it can be leveraged by an AI agent in conjunction with other tools (click, navigation, downloads) to perform unintended actions.

From the tool's definition Tool description states 'Start the browser (if not already running)' — this triggers an external operation (browser instantiation) whose effects depend on the broader context of how the browser is subsequently controlled via sibling tools like click_element,…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_browser Rate-limited

start_browser 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_browser": {
      "limits": [
        {
          "counter": "start_browser_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 Navmcp, so you can run agents against it safely.

FAQ

Questions about start_browser

What does the start_browser tool do? +

Start the browser (if not already running). It is categorised as a Execute tool in the Navmcp 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_browser? +

Register the Nav MCP server in PolicyLayer and add a rule for start_browser: 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 Navmcp. Nothing to install.

What risk level is start_browser? +

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

Can I rate-limit start_browser? +

Yes. Add a rate_limit block to the start_browser 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_browser completely? +

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

start_browser is provided by the Nav MCP server (jianlins/navmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.