KSEI MCP
An unofficial MCP server for accessing KSEI (AKSes) portfolio data, including cash balances, equity holdings, mutual funds, bonds, and other investments.
README
KSEI MCP
An unofficial Model Context Protocol (MCP) server for accessing your AKSes KSEI (Acuan Kepemilikan Sekuritas Kustodian Sentral Efek Indonesia) portfolio data.
This server enables AI assistants to retrieve Indonesian securities portfolio information, including:
- Cash balances
- Equity holdings
- Mutual funds
- Bonds
- Other investments
๐ง Prerequisites
- Python 3.11 or higher
- Valid KSEI account credentials
uvinstalled (recommended for quick execution)
โ๏ธ Installation & Setup
1. Set Environment Variables
Set the following environment variables:
export KSEI_USERNAME="your_ksei_username"
export KSEI_PASSWORD="your_ksei_password"
export KSEI_AUTH_PATH="./data" # Optional, defaults to "./data" for saving auth tokens
2. Run with uvx (Recommended)
The easiest way to start the server is with uvx:
# Run directly from PyPI
uvx ksei-mcp
# Or run from the local directory
uvx --from . ksei-mcp
3. Alternative: Traditional Installation
If you prefer manual installation:
# Install dependencies
pip install -e .
๐ค Usage with MCP Clients
Add this configuration to your MCP-compatible client:
{
"mcpServers": {
"ksei": {
"type": "stdio",
"command": "uvx",
"args": ["ksei-mcp@latest"]
}
}
}
๐งช Development: Using MCP Inspector
For local testing and development:
# Install MCP Inspector
npm install -g @modelcontextprotocol/inspector
# Run with inspector
mcp-inspector uvx --from . ksei-mcp
๐ฌ Example Queries
Once integrated into your AI assistant, you can ask:
"Show me my KSEI portfolio summary"
"What are my current cash balances?"
"List all my equity holdings"
"Get my mutual fund investments"
"Fetch all portfolio data"
Example (Using Gemini CLI)

Other supported clients include GitHub Copilot, Claude, and any MCP-compatible assistant.
๐ Security Considerations
- Credentials: Never commit credentials to version control. Use environment variables or secure vaults.
- Token Storage: Auth tokens are stored locally as JSON files.
- Secure Transport: All communication with KSEI uses HTTPS.
- Access Control: Restrict file system access to the authentication and data directories.
๐ ๏ธ Contributing
- Fork this repository
- Create a feature branch
- Implement your changes
- Add tests (if applicable)
- Open a pull request
๐ License
Licensed under the MIT License. See the LICENSE file for details.
โ ๏ธ Disclaimer
This software is intended for educational and personal use only. Users are responsible for complying with KSEI's terms of service and all relevant regulations.
Note: This is an unofficial client for KSEI services. It is not affiliated with or endorsed by KSEI.
Acknowledgement
This project is an adaptation from chickenzord/goksei. Many thanks to the original author for their work and inspiration.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.