home / mcp / lpdp mcp server

LPDP MCP Server

MCP Server for LPDP Scholarship Disbursement FAQ - RAG with Pinecone and Gemini 2.0 Flash

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "adityaldy-mcp-training": {
      "command": "python",
      "args": [
        "-m",
        "src.server"
      ],
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
        "PINECONE_API_KEY": "YOUR_PINECONE_API_KEY"
      }
    }
  }
}

You can deploy the LPDP MCP Server to answer questions about LPDP scholarship withdrawal procedures using Retrieval Augmented Generation (RAG) with Pinecone and Gemini 2.0 Flash. This server lets you ask questions, get precise answers from the LPDP withdrawal guide, and use fast semantic search to locate relevant information.

How to use

Launch the LPDP MCP Server in your environment and connect an MCP client (such as Claude Desktop or similar MCP-enabled frontend). You will interact with a dedicated MPLP-like endpoint that answers questions about LPDP withdrawal procedures. Your client can ask general questions, query for specific document sections, and request information like deadlines or required documents. The server uses a vector search backend to retrieve relevant passages and then generates a concise answer in Indonesian with good language support.

How to install

Prerequisites you need before installing: Python 3.10+ (required for MCP SDK), Pinecone account (free tier), Google AI API key.

# 1) Clone the MCP server repository
git clone <repository-url>
cd training-vibecode-mcp

# 2) Ensure Python 3.11 is installed if not already (optional step in some guides)
# macOS
brew install [email protected]

# Ubuntu/Debian
sudo apt update
sudo apt install python3.11 python3.11-venv

# 3) Create and activate a virtual environment
python3.11 -m venv venv
source venv/bin/activate  # Linux/macOS
# or
.\venv\Scripts\activate  # Windows

# 4) Install dependencies
pip install -r requirements.txt
```

```bash
# 5) Setup environment variables
cp .env.example .env
# Edit .env with your API keys (PINECONE_API_KEY, GOOGLE_API_KEY, etc.)

# 6) Index documents into Pinecone before running the server
python -m scripts.index_documents

# 7) Run in standalone mode
python -m src.server

Additional configuration and notes

If you plan to integrate with Claude Desktop as an MCP client, you can configure the LPCP server under your Claude Desktop MCP settings with the following stdio configuration. This runs the server locally and passes the required environment keys.

{
  "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"
      }
    }
  }
}

Available tools

tanya_pencairan_lpdp

Answer common questions about LPDP fund disbursement and withdrawal procedures.

cari_komponen_dana

Search for specific fund components within the LPDP funding guidelines.

cek_batas_waktu

Check submission deadlines for fund withdrawal requests.

info_dana_bulanan

Provide monthly living allowance information by country or city.

cari_dokumen_persyaratan

Retrieve documents required for withdrawal applications.