annotate_pdf
AI agents use annotate_pdf to create or update resources in oxidize-pdf MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your oxidize-pdf MCP Server environment.
Annotation is a reversible modification operation that adds comments, highlights, or markup to PDFs without destructively altering core content or deleting data. It fits the Write category (creates/modifies data reversibly). Severity is medium because misuse could add misleading or malicious annotations to documents, but the change is non-destructive and can be corrected or removed.
From the tool's definition Tool name 'annotate_pdf' indicates modification of PDF documents. Server context shows tools for 'PDF generation, parsing, splitting, merging, and manipulation'.
Attacks that exploit this kind of access
annotate_pdf. It is categorised as a Write tool in the oxidize-pdf MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the oxidize-pdf MCP Server MCP server in PolicyLayer and add a rule for annotate_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 oxidize-pdf MCP Server. Nothing to install.
annotate_pdf is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the annotate_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 annotate_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.
annotate_pdf 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 →