AI agents use browser_video_save to create or update resources in Playwright MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Playwright MCP environment.
The tool writes data (video content) to disk at a caller-specified path. While not irreversible deletion, it can overwrite existing files and consume storage. This is a Write action (creates/modifies files) rather than Execute because the operation itself is deterministic—it saves video without running arbitrary code.
From the tool's definition Tool name is 'browser_video_save' and description translates to 'saves video from current tab to specified path'. This tool creates/writes a file to the filesystem at a user-specified location.
Documented attack patterns abuse exactly the kind of access browser_video_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_video_save:
{
"version": "1",
"default": "deny",
"tools": {
"browser_video_save": {
"limits": [
{
"counter": "browser_video_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}browser_video_save stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
현재 탭의 비디오를 지정된 경로에 저장합니다. It is categorised as a Write tool in the Playwright MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_video_save: 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 MCP. Nothing to install.
browser_video_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_video_save 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.
Set action: deny in the PolicyLayer policy for browser_video_save. 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.
browser_video_save is provided by the Playwright MCP server (korwabs/playwright-record-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 Playwright MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.