Pinata MCP

Instructions

Implementation Reference

• src/index.ts:1712-1747 (registration)

  Registration and handler for the vectorizeFile tool - makes a POST request to Pinata's vectorize API to enable AI/semantic search on a file

  server.tool(
    "vectorizeFile",
    "Vectorize a file for AI/semantic search capabilities",
    {
      file_id: z.string().describe("ID of the file to vectorize"),
    },
    async ({ file_id }) => {
      try {
        const url = `https://uploads.pinata.cloud/v3/vectorize/files/${file_id}`;
  
        const response = await fetch(url, {
          method: "POST",
          headers: getHeaders(),
        });
  
        if (!response.ok) {
          const errorText = await response.text();
          throw new Error(
            `Failed to vectorize file: ${response.status} ${response.statusText}\n${errorText}`
          );
        }
  
        const data = await response.json();
        return {
          content: [
            {
              type: "text",
              text: `✅ File vectorized successfully!\n\n${JSON.stringify(data, null, 2)}`,
            },
          ],
        };
      } catch (error) {
        return errorResponse(error);
      }
    }
  );

• src/index.ts:1715-1717 (schema)

  Input schema definition for vectorizeFile - accepts a file_id string parameter

  {
    file_id: z.string().describe("ID of the file to vectorize"),
  },