find_and_highlight_text
AI agents call find_and_highlight_text to retrieve information from PDF Reader MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'Find and highlight' describes a query and visual annotation operation with no side effects that persist or alter the document's content. It retrieves text and applies temporary or visual-only markup, consistent with Read category behavior. Absence of description lowers confidence slightly, but the function name and server context strongly suggest a read-only operation.
From the tool's definition Tool name 'find_and_highlight_text' indicates text search and marking operations on PDFs. No description provided.
Attacks that exploit this kind of access
find_and_highlight_text. It is categorised as a Read tool in the PDF Reader MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PDF Reader MCP Server MCP server in PolicyLayer and add a rule for find_and_highlight_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 PDF Reader MCP Server. Nothing to install.
find_and_highlight_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 find_and_highlight_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 find_and_highlight_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.
find_and_highlight_text is provided by the PDF Reader MCP Server MCP server (lihongwen/pdfreadermcp). 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 →