groww
MCP server from arkapravasinha/groww-mcp-server
claude mcp add --transport stdio arkapravasinha-groww-mcp-server node server.js \ --env DEBUG="false" \ --env GROWW_API_KEY="your_groww_api_key_here"
How to use
Groww MCP Server provides a comprehensive adapter to Groww's trading platform, exposing a wide range of MCP endpoints for instrument discovery, order management, portfolio access, margin calculations, and both live and historical market data. The server includes capabilities to search and fetch instrument details, place and modify orders, retrieve order statuses, manage holdings and positions, compute margin requirements, and generate technical analysis indicators such as moving averages, RSI, Bollinger Bands, MACD, stochastic oscillators, and more. This makes it suitable for building algorithmic trading workflows, backtesting, or research dashboards that rely on programmatic access to Groww data and trading actions.
To use the server, run it with your Groww API key in the environment. Once running, you can interact with the exposed MCP endpoints using the typical MCP client tooling or custom scripts. The examples in the repository illustrate how to call search_instruments, place_order, get_live_quote, get_historical_data, and various technical analysis functions. The API surface is designed to be familiar to developers who have used MCP servers for other brokers, so you can plug it into existing MCP client tooling and pipelines with minimal changes.
How to install
Prerequisites
- Node.js (LTS version) installed on your machine
- npm or pnpm for package management
- Access to a Groww account with API access and a generated API key
Installation steps
-
Clone the repository
- git clone https://github.com/arkapravasinha-groww-mcp-server.git
- cd groww-mcp-server
-
Install dependencies
- npm install
-
Configure environment
- Create a .env file or export environment variables, for example: GROWW_API_KEY=your_groww_api_key_here DEBUG=false
-
Run the MCP server
- npm start
- Or if you run manually: node server.js
-
Verify locally
- Open http://localhost:PORT (if the server exposes a health/check endpoint) or use your MCP client to connect to the configured MCP endpoint.
Optional: If the project ships a Docker image
- Build and run
- docker build -t groww-mcp-server .
- docker run -e GROWW_API_KEY=your_groww_api_key_here -p 3000:3000 groww-mcp-server
Prerequisites (Docker): Docker installed and running.
Additional notes
Tips and common issues:
- Ensure your Groww API key has the required permissions for the endpoints you intend to use (instruments, orders, margin, etc.).
- If you encounter connection issues, double-check network access to Groww APIs and verify that the API key is correctly set in the environment.
- For production deployments, consider setting DEBUG to false and enabling proper logging and rate-limit handling.
- The server exposes a wide range of endpoints; refer to the usage examples in README for request shapes and required parameters.
- If you plan to run multiple MCP servers in parallel, assign distinct ports and environment configurations to avoid conflicts.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.