Extract all text from a PDF. If output_path given, also save to .txt.
AI agents call pdf_to_text to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and extracts text from a PDF file. While it can optionally save output to a .txt file (a Write side effect), its primary function is reading/extracting content. The write side effect is minor and reversible, but since the tool can also write a file, severity is bumped slightly. Overall, Read is the dominant action with a low blast radius.
From the tool's definition Extract all text from a PDF. If output_path given, also save to .txt.
Attacks that exploit this kind of access
Extract all text from a PDF. If output_path given, also save to .txt. It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for pdf_to_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 Nexus Core. Nothing to install.
pdf_to_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 pdf_to_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 pdf_to_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.
pdf_to_text is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →