akses-ksei-mcp

ichsanulamal/akses-ksei-mcp

3.1

If you are the rightful owner of akses-ksei-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The KSEI MCP Server is an unofficial Model Context Protocol server designed to fetch portfolio data from PT Kustodian Sentral Efek Indonesia (KSEI).

Tools
3
Resources
0
Prompts
0

KSEI MCP Server

Unofficial Model Context Protocol server for fetching AKSes KSEI portfolio data from PT Kustodian Sentral Efek Indonesia (KSEI).

Features

  • Smart Caching: Automatic caching with configurable TTL to reduce API calls
  • Multiple Portfolio Types: Support for ekuitas, reksadana, obligasi, kas, lainnya
  • Batch Operations: Fetch all portfolio types at once
  • Error Handling: Robust error handling with detailed feedback
  • Cache Management: Tools to clear cache when needed

Installation

npm install

Configuration

Copy .env.example to .env and configure:

cp .env.example .env

Required:

  • AUTH_TOKEN: Your KSEI API authorization token

Optional:

  • CACHE_DIR: Cache directory (default: ./storage/cache)
  • CACHE_TTL: Cache TTL in milliseconds (default: 3600000 = 1 hour)

Usage

As MCP Server

npm start

Available Tools

  1. fetch_portfolio

    • Fetch specific portfolio type
    • Parameters: type (required), date (optional)

  2. fetch_all_portfolios

    • Fetch all portfolio types
    • Parameters: date (optional)

  3. clear_cache

    • Clear all cached data
    • No parameters required

MCP Client Configuration

Add to your MCP client config:

{
  "mcpServers": {
    "ksei": {
      "command": "node",
      "args": ["path/to/ksei-server.mjs"],
      "env": {
        "AUTH_TOKEN": "your_token_here"
      }
    }
  }
}

Cache Behavior

  • Cache files stored in CACHE_DIR with format: {type}_{date}.json
  • Automatic cache validation based on TTL
  • Cache hit indicated by _cached: true in response
  • Fresh data indicated by _cached: false

Error Handling

The server handles various error scenarios:

  • Missing auth token
  • Network failures
  • Invalid API responses
  • Cache read/write errors

All errors are properly propagated with meaningful messages.

Notes

  • Educational Use Only: This tool is intended for educational purposes. Please review KSEI's Terms of Service and Conditions for any restrictions on data usage.
  • Data Accuracy: The accuracy and availability of data depend on the KSEI website.

Contributing

Contributions are welcome! If you find any issues or have suggestions for improvements, feel free to open an issue or submit a pull request.

License

This project is licensed under the MIT License.