extract_pdf_text
AI agents call extract_pdf_text to retrieve information from Funky Junction without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read operation—extracting and retrieving text data from a PDF document. There are no side effects, data modifications, code execution, or destructive actions. The empty description lowers confidence slightly, but the name unambiguously describes a data retrieval function. Severity is low because extracting text from PDFs poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'extract_pdf_text' indicates retrieval/extraction of text content from PDF files with no modification or execution.
Attacks that exploit this kind of access
extract_pdf_text. It is categorised as a Read tool in the Funky Junction MCP Server, which means it retrieves data without modifying state.
Register the Funky Junction MCP server in PolicyLayer and add a rule for extract_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 Funky Junction. Nothing to install.
extract_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 extract_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 extract_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.
extract_pdf_text is provided by the Funky Junction MCP server (paulgoldschmidt/qsim-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 →