AI agents call pinchtab_screenshot to retrieve information from Pinchtab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves visual information from the current browser state. It has no side effects, does not modify data, does not execute commands, and does not move data or delete anything. It is a straightforward information retrieval operation analogous to capturing the current state for inspection.
From the tool's definition Tool description states 'Take a screenshot of the page. Returns a base64-encoded image.' Screenshots are read-only operations that capture visual state without modifying any data or executing code.
Attacks that exploit this kind of access
Take a screenshot of the page. Returns a base64-encoded image. It is categorised as a Read tool in the Pinchtab MCP Server, which means it retrieves data without modifying state.
Register the Pinchtab MCP server in PolicyLayer and add a rule for pinchtab_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 Pinchtab. Nothing to install.
pinchtab_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 pinchtab_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 pinchtab_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.
pinchtab_screenshot is provided by the Pinchtab MCP server (maderwin/pinchtab-mcp). 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 →