docx_to_html
Convert DOCX files to HTML format while maintaining original structure and layout using Simple Document Processing MCP Server.
Instructions
Convert DOCX to HTML while preserving formatting
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputPath | Yes | Path to the input DOCX file | |
| outputDir | Yes | Directory where HTML should be saved |
Input Schema (JSON Schema)
{
"properties": {
"inputPath": {
"description": "Path to the input DOCX file",
"type": "string"
},
"outputDir": {
"description": "Directory where HTML should be saved",
"type": "string"
}
},
"required": [
"inputPath",
"outputDir"
],
"type": "object"
}
Implementation Reference
- src/tools/docxTools.ts:59-98 (handler)The core handler function that reads the DOCX file, converts it to HTML using the mammoth library, saves it with a unique filename in the output directory, and returns success/error info.export async function docxToHtml(inputPath: string, outputDir: string) { try { console.error(`Starting DOCX to HTML conversion...`); 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 buffer = await fs.readFile(inputPath); const result = await mammoth.convertToHtml({ buffer }); console.error( `Conversion completed with ${result.messages.length} messages` ); const outputPath = path.join(outputDir, `converted_${uniqueId}.html`); await fs.writeFile(outputPath, result.value); console.error(`Written HTML to ${outputPath}`); return { success: true, data: `Successfully converted DOCX to HTML: ${outputPath}`, }; } catch (error) { console.error(`Error in docxToHtml:`, error); return { success: false, error: error instanceof Error ? error.message : "Unknown error", }; } }
- src/tools/docxTools.ts:15-32 (schema)The tool definition including name, description, and input schema for validation.export const DOCX_TO_HTML_TOOL: Tool = { name: "docx_to_html", description: "Convert DOCX to HTML while preserving formatting", inputSchema: { type: "object", properties: { inputPath: { type: "string", description: "Path to the input DOCX file", }, outputDir: { type: "string", description: "Directory where HTML should be saved", }, }, required: ["inputPath", "outputDir"], }, };
- src/tools/_index.ts:9-9 (registration)The DOCX_TO_HTML_TOOL is imported and included in the central tools array for registration in the MCP server.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/index.ts:132-148 (registration)Server request handler dispatches 'docx_to_html' tool calls by extracting arguments and invoking the docxToHtml handler function.if (name === "docx_to_html") { const { inputPath, outputDir } = args as { inputPath: string; outputDir: string; }; const result = await docxToHtml(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/docxTools.ts:10-12 (helper)Helper function to generate unique ID for output filenames.function generateUniqueId(): string { return randomBytes(9).toString("hex"); }