extract_text
AI agents call extract_text to retrieve information from oxidize-pdf MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Extract_text retrieves or queries textual content from PDFs without modifying or deleting data. This is a classic Read operation with minimal blast radius—the primary risk is information disclosure if sensitive PDF content is extracted without authorization, but the tool itself performs no side effects.
From the tool's definition Tool name 'extract_text' combined with server's stated capability for 'parsing' and 'extraction' indicates data retrieval. Sibling tool 'extract_entities' and 'read_pdf' confirm the Read category pattern on this server.
Attacks that exploit this kind of access
extract_text. It is categorised as a Read tool in the oxidize-pdf MCP Server MCP Server, which means it retrieves data without modifying state.
Register the oxidize-pdf MCP Server MCP server in PolicyLayer and add a rule for extract_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 oxidize-pdf MCP Server. Nothing to install.
extract_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_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_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_text is provided by the oxidize-pdf MCP Server MCP server (bzsanti/oxidize-python). 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 →