Dumpling AI MCP Server

Instructions

Implementation Reference

• src/index.ts:423-437 (handler)

  The handler function for the 'extract' tool. It fetches the API key, makes a POST request to the Dumpling AI extract endpoint with the url and schema, handles errors, and returns the JSON response as text content.

  async ({ url, schema }) => {
    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/extract`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${apiKey}`,
      },
      body: JSON.stringify({ url, schema }),
    });
    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:419-422 (schema)

  Input schema for the 'extract' tool using Zod, defining 'url' as a URL string and 'schema' as a record of any type.

  {
    url: z.string().url().describe("URL to extract from"),
    schema: z.record(z.any()).describe("Schema defining the data to extract"),
  },

• src/index.ts:415-439 (registration)

  Full registration of the 'extract' tool on the MCP server, including name, description, schema, and inline handler.

  // Tool to extract structured data from web pages
  server.tool(
    "extract",
    "Extract structured data from web pages using AI-powered instructions.",
    {
      url: z.string().url().describe("URL to extract from"),
      schema: z.record(z.any()).describe("Schema defining the data to extract"),
    },
    async ({ url, schema }) => {
      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/extract`, {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
          Authorization: `Bearer ${apiKey}`,
        },
        body: JSON.stringify({ url, schema }),
      });
      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) }] };
    }
  );