AI agents call get-screenshot to retrieve information from Playwright MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures visual state of a web page and returns an image. It performs only observation and retrieval; it does not modify, execute, delete, or interact with external systems or financial operations. The blast radius if misused by an AI agent is minimal — at worst, it reveals information already visible to the user in the browser.
From the tool's definition Tool name is 'get-screenshot' and description states 'Get a screenshot of the current page' — this is a retrieval operation with no side effects on the system or data.
Documented attack patterns abuse exactly the kind of access get-screenshot 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 get-screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"get-screenshot": {}
}
}get-screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a screenshot of the current page. It is categorised as a Read tool in the Playwright MCP MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP server in PolicyLayer and add a rule for get-screenshot: 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.
get-screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get-screenshot 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 get-screenshot. 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.
get-screenshot is provided by the Playwright MCP server (qabyai/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Playwright MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Playwright MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.