browser_start_video

A execute tool on the Playwright MCP server.

SERVERPlaywright SOURCEhanato238/playwright-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/hanato238-playwright-mcp/browser-start-video.md

WHAT IT DOES

What browser_start_video does on Playwright

AI agents invoke browser_start_video to trigger actions in Playwright. 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.

RISK

Why browser_start_video is rated High

This tool initiates a recording action in the browser context, which is an external operation with side effects (the recording will capture subsequent browser activity). While not destructive or financial, it fits the Execute category—it triggers an operation whose outcome depends on what happens after invocation.

From the tool's definition Tool 'browser_start_video' is part of a browser automation server (@playwright/mcp) whose core purpose is to 'interact with web pages' through automation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_start_video safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Playwright, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_start_video, this is the rule to start with:

browser_start_video Rate-limited

browser_start_video 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_start_video": {
      "limits": [
        {
          "counter": "browser_start_video_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Playwright, apply this rule, and every browser_start_video call is checked against it from then on.

FAQ

Questions about browser_start_video

What does the browser_start_video tool do? +

browser_start_video is a execute tool on the Playwright MCP server. It is categorised as a Execute tool in the Playwright 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_start_video? +

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

What risk level is browser_start_video? +

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

Can I rate-limit browser_start_video? +

Yes. Add a rate_limit block to the browser_start_video 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_start_video completely? +

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

browser_start_video is provided by the Playwright MCP server (hanato238/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Playwright, and thousands of servers like it.

This server

All 66 Playwright tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server →team_manager_start_room on Team Manager MCP →start_etw_trace on Procmon → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →