read-pdf-metadata

Extract metadata from PDF files using URLs or base64-encoded content to analyze document properties and structure for content processing workflows.

Instructions

Extract metadata from PDF files.

Input Schema

TableJSON Schema

Name	Required	Description
`inputMethod`	Yes	Input method
`files`	Yes	Array of URLs or base64-encoded PDFs
`requestSource`	No	Request source

Implementation Reference

src/index.ts:802-816 (handler)

Handler function that proxies the request to an external NWS API endpoint to read PDF metadata, using the provided API key and input parameters.

async ({ inputMethod, files, requestSource }) => {
  const apiKey = process.env.DUMPLING_API_KEY;
  if (!apiKey) throw new Error("DUMPLING_API_KEY not set");
  const response = await fetch(`${NWS_API_BASE}/api/v1/read-pdf-metadata`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: `Bearer ${apiKey}`,
    },
    body: JSON.stringify({ inputMethod, files, requestSource }),
  });
  if (!response.ok)
    throw new Error(`Failed: ${response.status} ${await response.text()}`);
  const data = await response.json();
  return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };

src/index.ts:797-801 (schema)

Zod schema for input validation: inputMethod as 'url' or 'base64', array of files (URLs or base64), optional requestSource.

{
  inputMethod: z.enum(["url", "base64"]).describe("Input method"),
  files: z.array(z.string()).describe("Array of URLs or base64-encoded PDFs"),
  requestSource: z.string().optional().describe("Request source"),
},

src/index.ts:794-818 (registration)

Registration of the 'read-pdf-metadata' tool on the MCP server, specifying name, description, input schema, and handler function.

server.tool(
  "read-pdf-metadata",
  "Extract metadata from PDF files.",
  {
    inputMethod: z.enum(["url", "base64"]).describe("Input method"),
    files: z.array(z.string()).describe("Array of URLs or base64-encoded PDFs"),
    requestSource: z.string().optional().describe("Request source"),
  },
  async ({ inputMethod, files, requestSource }) => {
    const apiKey = process.env.DUMPLING_API_KEY;
    if (!apiKey) throw new Error("DUMPLING_API_KEY not set");
    const response = await fetch(`${NWS_API_BASE}/api/v1/read-pdf-metadata`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${apiKey}`,
      },
      body: JSON.stringify({ inputMethod, files, requestSource }),
    });
    if (!response.ok)
      throw new Error(`Failed: ${response.status} ${await response.text()}`);
    const data = await response.json();
    return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
  }
);

Dumpling AI MCP Server