Extract figures, tables, and equations from PDF documents using layout detection. Perfect for extracting visual elements from academic papers on arXiv or any PDF URL. Returns base64-encoded images of detected elements with metadata.
AI agents call extract_pdf to retrieve information from Jina AI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | — | arXiv paper ID (e.g., '2301.12345' or 'hep-th/9901001'). Either id or url is required. |
url | string | — | Direct PDF URL. Either id or url is required. |
type | string | — | Filter by float types (comma-separated): figure, table, equation. If not specified, returns all types. |
max_edge | number | — | Maximum edge size for extracted images in pixels (default: 1024) |
Parameters from the server's own tool schema.
This tool retrieves and extracts visual content from PDF documents for analysis purposes. It has no side effects—it reads structured data from documents and returns it in a processable format (base64-encoded images and metadata). There is no capability to modify, delete, or execute operations.
From the tool's definition Tool 'extract_pdf' performs extraction of figures, tables, and equations from PDF documents and returns base64-encoded images with metadata.
Risk signalsAccepts URL/endpoint input (url)
Documented attack patterns abuse exactly the kind of access extract_pdf gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jina AI, and nothing reaches the server without passing your rules. This is the rule we recommend for extract_pdf:
{
"version": "1",
"default": "deny",
"tools": {
"extract_pdf": {}
}
}extract_pdf is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Extract figures, tables, and equations from PDF documents using layout detection. Perfect for extracting visual elements from academic papers on arXiv or any PDF URL. Returns base64-encoded images of detected elements with metadata. It is categorised as a Read tool in the Jina AI MCP Server, which means it retrieves data without modifying state.
extract_pdf accepts 4 parameters: id, url, type, max_edge. The full parameter table on this page comes from the server's own tool schema.
Register the Jina AI MCP server in PolicyLayer and add a rule for extract_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 Jina AI. Nothing to install.
extract_pdf 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 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. 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 is provided by the Jina AI MCP server (jina). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jina AI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Jina AI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.