OfficeCLI MCP Serverless for Gemini Spark
A stateless MCP server that wraps OfficeCLI to create and edit Microsoft Word documents via AI instructions, outputting Base64 Data URLs for serverless environments like Vercel.
README
OfficeCLI MCP Serverless for Gemini Spark
Stateless & Serverless Model Context Protocol (MCP) server yang membungkus OfficeCLI untuk membuat dan mengedit dokumen Microsoft Word (.docx) langsung melalui instruksi AI di Gemini Spark Custom App.
🚀 Fitur Utama
- Stateless & Serverless Ready: Didesain khusus untuk runtime Vercel Functions (
/tmpscratch space, auto-cleanup). - Batch Pipeline Execution: Menjalankan kumpulan perintah OfficeCLI secara berurutan dalam satu turn request.
- Base64 Data URL Output: Menghasilkan file Word langsung dalam format Base64 Data URL tanpa perlu external storage (S3/Blob).
- Auto Binary Provisioning: Otomatis mengunduh atau menyiapkan executable
officecliLinux x86_64 di environment serverless.
🛠️ Tool MCP yang Tersedia
generate_office_document
Mengeksekusi batch perintah OfficeCLI untuk membuat atau mengubah dokumen .docx.
Parameter Input:
filename(string, required): Nama file output (contoh:Laporan_Proyek.docx).commands(string[], required): Daftar perintah OfficeCLI yang dieksekusi berurutan.[ "create output.docx", "add output.docx / --type paragraph --prop \"text=Laporan Evaluasi Kuartal 3\"", "add output.docx / --type table --prop rows=3 --prop cols=3" ]initial_file_base64(string, optional): Base64 string dokumen awal jika ingin melakukan edit pada template existing.
📦 Menghubungkan ke Gemini Spark Custom App
-
Deploy ke Vercel:
pnpm install vercel deploy --prod -
Salin URL hasil deploy Vercel Anda, misalnya:
https://officecli-mcp.vercel.app/api/index -
Tambahkan ke Gemini Spark:
- Buka pengaturan Gemini Spark Custom App / Custom Tools / MCP Servers.
- Masukkan Server URL:
https://officecli-mcp.vercel.app/api/index(Transport: SSE / HTTP Remote MCP). - Simpan dan mulai perintahkan Gemini:
"Buatkan saya dokumen Word tentang laporan bisnis lengkap dengan tabel metrik!"
💻 Development & Testing Lokal
# Install dependencies
pnpm install
# Menjalankan unit tests
pnpm test
# Menjalankan MCP server di mode stdio
pnpm dev
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.