About Nuvama-MCP π οΈ
Nuvama-MCP connects Claude to Nuvama's trading APIs through an MCP server. It exposes tools to place stock buy and sell orders and retrieve holdings.
Key features
- 01Place stock buy orders
- 02Place stock sell orders
- 03Fetch holdings from the API
Use cases
- 01Submit stock orders through Claude
- 02Review holdings through an MCP client
MCP support
A FastMCP server exposes buy-order and sell-order tools for MCP clients; the README also describes fetching holdings from the API.
Configuration
Local server config is the same for every client. Copy it into your clientβs MCP config file.
We havenβt collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMENuvama-MCP π οΈ
This project integrates Nuvama's trading platform with Claude AI using the MCP framework, allows you to interact with nuvama trading platform directly through claude AI.
Features β¨
- π Place buy and sell orders for stocks.
- π Fetch and display holdings from the API.
- β‘ FastMCP server integration for easy tool access.
Project Structure π
- index.py: Contains the core logic for interacting with the trading API.
- trade_mcp_server.py: Implements a FastMCP server to expose trading functionalities as tools.
- .gitignore: Specifies files and directories to be ignored by Git.
Prerequisites β
- π Python 3.x installed on your system.
- π¦ Required Python packages installed (e.g., FastMCP, APIConnect).
- π API credentials (API key, secret, and request ID).
- π A CSV file containing stock symbols and exchange details.
Setup Instructions π οΈ
-
Clone the repository to your local machine.
-
Install the required Python packages:
pip install -r requirements.txt -
Update the following placeholders in
index.py:api_key: Your API key.api_secret: Your API secret.request_id: Your request ID.settings_file: Path to your settings file.csv_file_path: Path to your instruments CSV file.
-
Run the FastMCP server:
uv run trade_mcp_server.py
Using the MCP Tools π οΈ
The FastMCP server exposes the following tools:
- π buyorder: Place a buy order.
- ποΈ sellorder: Place a sell order.
You can call these tools directly from the MCP interface.
Configuring Claude for MCP Integration π€
To enable Claude to recognize the MCP tools, create a configuration file (e.g., claude_config.json) in the appropriate directory and add the following content:
{
"mcpServers": {
"trade": {
"command": "<path_to_uv_executable>",
"args": [
"--directory",
"<path_to_trade_directory>",
"run",
"trade_server.py"
]
}
}
}
Replace <path_to_uv_executable> with the path to your uv.exe file and <path_to_trade_directory> with the path to your project directory. Place this configuration file in the relevant location for Claude to detect it.
This configuration allows Claude to interact with the MCP tools, enabling you to place orders directly from Claude using Natural Language.
Happy Trading! π
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.