Skip to main content
Glama

open_document

Access and interact with Word documents by specifying the file path, enabling AI-powered reading and editing through natural language.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filePathYes

Implementation Reference

  • Core handler function that reads the document file and extracts its raw text content using the mammoth library, returning success or error response.
    async openDocument(filePath: string): Promise<APIResponse> { try { const buffer = await fs.readFile(filePath); const result = await mammoth.extractRawText({ buffer }); return { success: true, data: { content: result.value } }; } catch (error) { const err = error as Error; return { success: false, error: `打开文档失败: ${err.message}` }; } }
  • MCP server tool registration for 'open_document', including Zod input schema and thin wrapper that calls the DocumentService handler.
    server.tool( "open_document", { filePath: z.string(), }, async (params) => { const result = await docService.openDocument(params.filePath); return { content: [ { type: "text", text: result.success ? result.data!.content : result.error!, }, ], isError: !result.success, }; } );
  • JSON Schema definition for the 'open_document' tool input parameters in the HTTP server's tools list.
    { name: 'open_document', description: '打开 Word 文档', parameters: { properties: { filePath: { type: 'string', description: '文档路径' }, }, required: ['filePath'], type: 'object', }, },
  • src/server.ts:129-131 (registration)
    Dispatch handler registration in the HTTP server's switch statement for executing 'open_document' tool.
    case 'open_document': result = await docService.openDocument(parameters.filePath); break;

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/puchunjie/doc-tools-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server