PDF 파일에서 키워드를 검색합니다.
AI agents call search_in_pdf to retrieve information from Compliance Scanner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries content from PDF documents based on keyword searches. It has no side effects, does not modify data, does not execute code, and does not delete anything. It is a straightforward read operation that fits the Read category with low severity due to its passive nature and limited blast radius.
From the tool's definition Tool name 'search_in_pdf' and description indicate searching for keywords within PDF files. The description in Korean states 'PDF 파일에서 키워드를 검색합니다' (searches for keywords in PDF files). This is a read-only query operation with no data modification or execution.
Attacks that exploit this kind of access
PDF 파일에서 키워드를 검색합니다. It is categorised as a Read tool in the Compliance Scanner MCP MCP Server, which means it retrieves data without modifying state.
Register the Compliance Scanner MCP server in PolicyLayer and add a rule for search_in_pdf: 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 Compliance Scanner MCP. Nothing to install.
search_in_pdf 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 search_in_pdf 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 search_in_pdf. 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.
search_in_pdf is provided by the Compliance Scanner MCP server (tae4an/compliance-scanner-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 →