What prerequisites are required?
You need Python, a Zerodha trading account with Personal API access (obtained from developers.kite.trade), and an OpenAI API key (for Agno) or Gemini API key or Application Default Credentials (for Google ADK).
@mtwn105
基本情報
Zerodha MCP Server & Client (Kite x Agno)
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"zerodha-mcp-mtwn105": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Python-based trading assistant that connects to a Zerodha MCP server to help users manage their trading account. It integrates with Zerodha’s API via the Model Context Protocol and supports both Agno and Google ADK agent frameworks for natural-language interaction.
Install dependencies, configure a .env file with Zerodha API credentials and an LLM API key (OpenAI for Agno, Gemini or ADC for Google ADK), then start the server with python server.py. Launch the client with python client/agno_client.py or python client/google_adk_client.py. Use the interactive chat to execute trading commands such as “Show me my holdings” or “Place a market order”.
You need Python, a Zerodha trading account with Personal API access (obtained from developers.kite.trade), and an OpenAI API key (for Agno) or Gemini API key or Application Default Credentials (for Google ADK).
Agno and Google ADK agent frameworks are both supported; choose either `agno_client.py` or `google_adk_client.py`.
Set `ZERODHA_API_KEY` and `ZERODHA_API_SECRET` in your `.env` file. For the client, also set `OPENAI_API_KEY` or `GOOGLE_API_KEY` as required.
The server can run in SSE mode or stdio mode, configured via `SERVER_MODE` in `.env` or the `--mode` command‑line argument.
Log in to [developers.kite.trade](https://developers.kite.trade/login) with your Zerodha credentials to generate your API key and secret.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Hindsight: Agent Memory That Learns

Model Context Protocol Servers

Model Context Protocol Servers

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
コメント