trade-mcp
An MCP server that lets a language model place real equity orders on a live Groww brokerage account.
README
trade-mcp
An MCP server that lets a language model place real equity orders on a live Groww brokerage account.
MCP (Model Context Protocol) is a standard that lets an AI client discover and call tools on an external server — here, that means letting Claude buy and sell stock.
This spends real money. It ships in DRY RUN mode and stays there until you deliberately turn it off.
Install
bun install
cp .env.example .env # then fill in your credentials
bun run smoke # verify the handshake without touching the brokerage
| Script | Purpose |
|---|---|
bun run start |
Run the server on stdio |
bun run dev |
Same, with reload on change |
bun run build |
Bundle to dist/index.js |
bun run typecheck |
tsc --noEmit |
bun run smoke |
Drive the server with hand-written JSON-RPC |
Tools
| Tool | Input | Effect |
|---|---|---|
buy_stock |
tradingSymbol (e.g. SBIN), quantity (positive integer) |
Places a MARKET BUY on NSE / CASH / CNC, DAY validity |
sell_stock |
same | Places a MARKET SELL, same defaults |
Only symbol and quantity are model-supplied. Exchange, segment, product, validity, and order type are server-side constants — the model cannot switch to intraday leverage, hop exchanges, or change the order type.
Both tools are annotated destructiveHint: true and openWorldHint: true so MCP clients prompt a human before invoking.
Adding a tool means writing one ToolDefinition and appending it to the array in src/tools/index.ts — server.ts iterates the registry and needs no edit. get_holdings, get_quote, and cancel_order are the obvious next ones; they map to groww.holdings.list, groww.liveData.getQuote, and groww.orders.cancel.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.