browser_intercept_start · Byob MCP: Risk & Policy

WHAT IT DOES

What browser_intercept_start does on Byob

AI agents invoke browser_intercept_start to trigger actions in Byob. 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 browser_intercept_start needs a policy

Request interception is an Execute-class action because it triggers external operations (network request handling) whose effects depend on how the arguments are configured. While not inherently destructive, it enables man-in-the-middle manipulation of web traffic, modifying requests/responses in real-time.

From the tool's definition Tool name 'browser_intercept_start' combined with server capability to 'control your real Chrome browser' indicates the ability to intercept and potentially manipulate HTTP requests in flight.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_intercept_start Rate-limited

browser_intercept_start 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": {
    "browser_intercept_start": {
      "limits": [
        {
          "counter": "browser_intercept_start_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 Byob, so you can run agents against it safely.

FAQ

Questions about browser_intercept_start

What does the browser_intercept_start tool do? +

Start a request-interception session in a tab. Provide an array of. It is categorised as a Execute tool in the Byob MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_intercept_start? +

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

What risk level is browser_intercept_start? +

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

Can I rate-limit browser_intercept_start? +

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

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

browser_intercept_start is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.