Dumpling AI MCP Server

Instructions

Implementation Reference

• src/index.ts:933-948 (handler)

  Handler function that executes the tool by sending a POST request to the external API endpoint to add text resources to a specified knowledge base.

  async ({ knowledgeBaseId, name, content }) => {
    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/knowledge-bases/add`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${apiKey}`,
      },
      body: JSON.stringify({ knowledgeBaseId, name, content }),
    });
    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:929-932 (schema)

  Zod schema defining the input parameters for the tool: knowledgeBaseId, name, and content.

    knowledgeBaseId: z.string().describe("Knowledge base ID"),
    name: z.string().describe("Resource name"),
    content: z.string().describe("Text content to add"),
  },

• src/index.ts:925-949 (registration)

  Registration of the 'add-to-knowledge-base' tool using server.tool(), including description, input schema, and handler function.

  server.tool(
    "add-to-knowledge-base",
    "Add new text resources to a knowledge base.",
    {
      knowledgeBaseId: z.string().describe("Knowledge base ID"),
      name: z.string().describe("Resource name"),
      content: z.string().describe("Text content to add"),
    },
    async ({ knowledgeBaseId, name, content }) => {
      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/knowledge-bases/add`, {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
          Authorization: `Bearer ${apiKey}`,
        },
        body: JSON.stringify({ knowledgeBaseId, name, content }),
      });
      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) }] };
    }
  );