convert_docx_to_html

Convert Microsoft Word DOCX files to clean HTML while preserving formatting, tables, and lists. This tool transforms document content for web use.

Instructions

Convert a DOCX file to HTML using mammoth. Supports reading from a file path and returns the HTML content.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`filePath`	Yes	Absolute path to the DOCX file to convert

Implementation Reference

src/index.ts:24-61 (handler)

The handler function that implements the core logic of the 'convert_docx_to_html' tool. It reads the DOCX file using mammoth, converts it to HTML, formats the output with markdown including the HTML code block and any messages, and handles errors.

async ({ filePath }) => {
  try {
    const absolutePath = path.resolve(filePath);
    await fs.access(absolutePath);

    const result = await mammoth.convertToHtml({ path: absolutePath });

    let output = `# Conversion Result\n\n`;
    output += `**File**: ${absolutePath}\n\n`;
    output += `## HTML Output:\n\n\`\`\`html\n${result.value}\n\`\`\`\n\n`;

    if (result.messages.length > 0) {
      output += `## Messages:\n\n`;
      result.messages.forEach((msg: any) => {
        output += `- ${msg.type}: ${msg.message}\n`;
      });
    }

    return {
      content: [
        {
          type: 'text',
          text: output,
        },
      ],
    };
  } catch (error) {
    return {
      content: [
        {
          type: 'text',
          text: `Error converting DOCX file: ${error instanceof Error ? error.message : String(error)}`,
        },
      ],
      isError: true,
    };
  }
}

src/index.ts:15-62 (registration)

The registration of the 'convert_docx_to_html' tool on the MCP server, specifying the tool name, description, input schema, and handler function.

server.registerTool(
  'convert_docx_to_html',
  {
    description:
      'Convert a DOCX file to HTML using mammoth. Supports reading from a file path and returns the HTML content.',
    inputSchema: {
      filePath: z.string().describe('Absolute path to the DOCX file to convert'),
    },
  },
  async ({ filePath }) => {
    try {
      const absolutePath = path.resolve(filePath);
      await fs.access(absolutePath);

      const result = await mammoth.convertToHtml({ path: absolutePath });

      let output = `# Conversion Result\n\n`;
      output += `**File**: ${absolutePath}\n\n`;
      output += `## HTML Output:\n\n\`\`\`html\n${result.value}\n\`\`\`\n\n`;

      if (result.messages.length > 0) {
        output += `## Messages:\n\n`;
        result.messages.forEach((msg: any) => {
          output += `- ${msg.type}: ${msg.message}\n`;
        });
      }

      return {
        content: [
          {
            type: 'text',
            text: output,
          },
        ],
      };
    } catch (error) {
      return {
        content: [
          {
            type: 'text',
            text: `Error converting DOCX file: ${error instanceof Error ? error.message : String(error)}`,
          },
        ],
        isError: true,
      };
    }
  }
);

src/index.ts:20-22 (schema)
The input schema for the tool, defining 'filePath' as a required string using Zod validation.
```
inputSchema: {
  filePath: z.string().describe('Absolute path to the DOCX file to convert'),
},
```

Mammoth MCP Server