Extract text from a PDF file (restricted to Applied Jobs and Auto output/logs).
AI agents call files.read_pdf_text to retrieve information from MCP Playwright Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries PDF content without side effects or modifications. It is a read-only operation constrained to specific, safe file categories (application outputs and logs), making it low-severity even if misused by an agent.
From the tool's definition Tool name 'read_pdf_text' and description 'Extract text from a PDF file' indicate data retrieval with no modification. Scope is explicitly restricted to 'Applied Jobs and Auto output/logs', limiting blast radius.
Attacks that exploit this kind of access
Extract text from a PDF file (restricted to Applied Jobs and Auto output/logs). It is categorised as a Read tool in the MCP Playwright Browser MCP Server, which means it retrieves data without modifying state.
Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for files.read_pdf_text: 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 MCP Playwright Browser. Nothing to install.
files.read_pdf_text 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 files.read_pdf_text 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 files.read_pdf_text. 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.
files.read_pdf_text is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). 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 →