web_extract_pdf
Extract text content from PDF files by providing a URL. This tool processes PDF documents to retrieve readable text for analysis or integration.
Instructions
Extract text content from any PDF URL. Costs $0.03 USDC per request via x402 on Base.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | PDF URL to extract text from |
Implementation Reference
- src/index.ts:319-334 (registration)The "web_extract_pdf" tool is registered here with its schema and handler implementation.
server.registerTool( "web_extract_pdf", { title: "Extract Text from PDF", description: `Extract text content from any PDF URL. Costs $0.03 USDC per request via x402 on Base.`, inputSchema: { url: z.string().url().describe("PDF URL to extract text from"), }, annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: true }, }, async ({ url }) => { const data = await apiPost(`${WEB_EXTRACT_API}/api/v1/extract/pdf`, { url }); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } );