LPDP MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LPDP MCP Serverberapa living allowance untuk mahasiswa di London?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LPDP MCP Server
MCP Server untuk menjawab pertanyaan seputar pencairan keuangan beasiswa LPDP menggunakan RAG (Retrieval Augmented Generation) dengan Pinecone dan Gemini 2.0 Flash.
๐ Fitur
RAG-powered Q&A: Menjawab pertanyaan berdasarkan dokumen Panduan Pencairan Awardee LPDP
Vector Search: Menggunakan Pinecone untuk pencarian semantik yang akurat
Gemini 2.0 Flash: Response cepat dengan dukungan bahasa Indonesia yang baik
MCP Protocol: Dapat diintegrasikan dengan Claude Desktop dan aplikasi AI lainnya
Related MCP server: AI Tutoring RAG System
๐ Prerequisites
Python 3.10+ (wajib untuk MCP SDK)
Pinecone account (free tier)
Google AI API key
๐ ๏ธ Instalasi
Clone repository:
git clone <repository-url>
cd training-vibecode-mcpInstall Python 3.11 (jika belum ada):
# macOS dengan Homebrew
brew install python@3.11
# Ubuntu/Debian
sudo apt update
sudo apt install python3.11 python3.11-venvBuat virtual environment:
python3.11 -m venv venv
source venv/bin/activate # Linux/macOS
# atau
.\venv\Scripts\activate # WindowsInstall dependencies:
pip install -r requirements.txtSetup environment variables:
cp .env.example .env
# Edit .env dengan API keys Anda๐ Indexing Dokumen
Sebelum menggunakan server, index dokumen PDF ke Pinecone:
python -m scripts.index_documents๐ฅ๏ธ Menjalankan Server
Sebagai MCP Server (untuk Claude Desktop)
Tambahkan konfigurasi berikut ke claude_desktop_config.json:
{
"mcpServers": {
"lpdp-pencairan": {
"command": "python",
"args": ["-m", "src.server"],
"cwd": "/path/to/training-vibecode-mcp",
"env": {
"PINECONE_API_KEY": "your_key",
"GOOGLE_API_KEY": "your_key"
}
}
}
}Standalone Mode
python -m src.server๐ง MCP Tools
Tool | Deskripsi |
| Menjawab pertanyaan umum tentang pencairan beasiswa |
| Mencari informasi komponen dana spesifik |
| Mengecek deadline pengajuan dana |
| Informasi living allowance per negara/kota |
| Dokumen yang dibutuhkan untuk pengajuan |
๐ Contoh Penggunaan
User: Berapa living allowance untuk mahasiswa di Jepang?
Bot: Living allowance untuk mahasiswa LPDP di Jepang adalah:
- Tokyo: JPY 195,000/bulan
- Kota lain: JPY 170,000/bulan๐งช Testing
pytest tests/๐ License
MIT License
Trigger workflow test - Fri Dec 5 16:03:22 WIB 2025
This server cannot be deployed
Maintenance
Related MCP Connectors
Ingest, manage, and retrieve documents for RAG-powered AI applications
India's financial MCP โ cards, loans, FDs, insurance, MFs; EMI/SIP/tax calcs; NAV lookup; RAG.
- Era ContextOAuthapp.era
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables querying and analysis of SEC filing documents through natural language. Uses Pinecone vector search with document summarization to help users retrieve and understand financial filings for various companies.1-
- FlicenseNot gradedqualityNot gradedmaintenanceEnables personalized AI tutoring by allowing students to upload PDF/DOCX study materials that are processed and indexed for semantic search. Provides intelligent responses based on the student's own learning materials using RAG technology.-
- AlicenseAqualityCmaintenanceEnables LLMs to search and retrieve PayNow Component documentation directly, accelerating system integration through natural language queries.1MIT
- AlicenseNot gradedqualityDmaintenanceTransforms static gemini-cli documentation into a queryable RAG service, enabling developers to ask questions about Gemini CLI in natural language and receive instant, accurate answers based on the official documentation directly within their workflow.9MIT