AI agents use convert_pdf_to_card_html to create or update resources in Pdf Card — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pdf Card environment.
This tool creates new HTML artifacts from PDF inputs, which is a reversible Write operation. The conversion is deterministic and non-destructive—original PDFs are unchanged, and generated HTML can be regenerated or deleted. No external APIs, financial transactions, code execution, or irreversible data destruction are implied. Local processing limits blast radius.
From the tool's definition Tool name indicates PDF conversion and HTML generation ('convert_pdf_to_card_html'). Server description states it 'Converts dense PDFs into... card-based HTML readers' and processes data 'locally'.
Attacks that exploit this kind of access
convert_pdf_to_card_html. It is categorised as a Write tool in the Pdf Card MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pdf Card MCP server in PolicyLayer and add a rule for convert_pdf_to_card_html: 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 Pdf Card. Nothing to install.
convert_pdf_to_card_html 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 convert_pdf_to_card_html 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 convert_pdf_to_card_html. 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.
convert_pdf_to_card_html is provided by the Pdf Card MCP server (velyan/pdf-card-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 →