Simple Document Processing MCP Server

Instructions

Implementation Reference

• src/tools/htmlTools.ts:300-338 (handler)

  The core handler function that implements the html_formatter tool logic: reads input HTML, parses with JSDOM, serializes (beautifies), generates unique filename, and saves to output directory.

  export async function formatHtml(inputPath: string, outputDir: string) {
    try {
      console.error(`Starting HTML formatting...`);
      console.error(`Input file: ${inputPath}`);
      console.error(`Output directory: ${outputDir}`);
  
      // 確保輸出目錄存在
      try {
        await fs.access(outputDir);
        console.error(`Output directory exists: ${outputDir}`);
      } catch {
        console.error(`Creating output directory: ${outputDir}`);
        await fs.mkdir(outputDir, { recursive: true });
        console.error(`Created output directory: ${outputDir}`);
      }
  
      const uniqueId = generateUniqueId();
      const htmlContent = await fs.readFile(inputPath, "utf-8");
      const dom = new JSDOM(htmlContent);
      const { document } = dom.window;
  
      // 格式化 HTML
      const formattedHtml = dom.serialize();
      const outputPath = path.join(outputDir, `formatted_${uniqueId}.html`);
      await fs.writeFile(outputPath, formattedHtml);
      console.error(`Written formatted HTML to ${outputPath}`);
  
      return {
        success: true,
        data: `Successfully formatted HTML: ${outputPath}`,
      };
    } catch (error) {
      console.error(`Error in formatHtml:`, error);
      return {
        success: false,
        error: error instanceof Error ? error.message : "Unknown error",
      };
    }
  }

• src/tools/htmlTools.ts:93-110 (schema)

  The Tool object defining the schema, name, and description for the html_formatter tool.

  export const HTML_FORMAT_TOOL: Tool = {
    name: "html_formatter",
    description: "Format and beautify HTML code",
    inputSchema: {
      type: "object",
      properties: {
        inputPath: {
          type: "string",
          description: "Path to the input HTML file",
        },
        outputDir: {
          type: "string",
          description: "Directory where formatted HTML should be saved",
        },
      },
      required: ["inputPath", "outputDir"],
    },
  };

• src/index.ts:222-238 (registration)

  Registration and dispatch logic in the main CallToolRequestSchema handler: matches tool name and invokes the formatHtml function.

  if (name === "html_formatter") {
    const { inputPath, outputDir } = args as {
      inputPath: string;
      outputDir: string;
    };
    const result = await formatHtml(inputPath, outputDir);
    if (!result.success) {
      return {
        content: [{ type: "text", text: `Error: ${result.error}` }],
        isError: true,
      };
    }
    return {
      content: [{ type: "text", text: fileOperationResponse(result.data) }],
      isError: false,
    };
  }

• src/tools/_index.ts:9-9 (registration)

  The tools array export that registers HTML_FORMAT_TOOL for the ListToolsRequestSchema.

  export const tools = [DOCUMENT_READER_TOOL, PDF_MERGE_TOOL, PDF_SPLIT_TOOL, DOCX_TO_PDF_TOOL, DOCX_TO_HTML_TOOL, HTML_CLEAN_TOOL, HTML_TO_TEXT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, TEXT_DIFF_TOOL, TEXT_SPLIT_TOOL, TEXT_FORMAT_TOOL, TEXT_ENCODING_CONVERT_TOOL, EXCEL_READ_TOOL, FORMAT_CONVERTER_TOOL];

• src/tools/htmlTools.ts:8-10 (helper)

  Helper function generateUniqueId used in formatHtml to create unique output filenames.

  function generateUniqueId(): string {
    return randomBytes(9).toString("hex");
  }