Take a screenshot of the Web-LLM interface
AI agents call playwright_llm_screenshot to retrieve information from Web-LLM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot is a read-only operation that observes the current state of the Web-LLM interface without creating, modifying, deleting, or executing any operations. It has no side effects on data or system state. The blast radius of misuse is minimal—at worst, sensitive information visible on screen could be captured, but the action itself is non-destructive and reversible.
From the tool's definition Tool name 'playwright_llm_screenshot' and description 'Take a screenshot of the Web-LLM interface' indicate this retrieves/captures visual state of the interface without modifying any data or triggering side effects.
Attacks that exploit this kind of access
Take a screenshot of the Web-LLM interface. It is categorised as a Read tool in the Web-LLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Web-LLM MCP Server MCP server in PolicyLayer and add a rule for playwright_llm_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 Web-LLM MCP Server. Nothing to install.
playwright_llm_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 playwright_llm_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 playwright_llm_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.
playwright_llm_screenshot is provided by the Web-LLM MCP Server MCP server (ragingwind/web-llm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →