🚀 Build an AI-Powered Stock Market Research Assistant using OpenAPI Tools + MCP (in 5 Minutes)
Ever wanted to talk to the stock market like a research analyst?
I just built a personal stock research assistant for Indian markets—powered by OpenAPI Tools + MCP (Model Context Protocol)—and it only took about 5 minutes. 💬📈
With it, you can ask questions like:
- “Give me the last 5 years of stock performance for INFY”
- “What are the top 10 BSE movers today?”
- “Show me upcoming IPOs in India this month”
- “Which mutual funds have outperformed the index recently?”
Built using GenAI, OpenAPI schemas, and the MCP standard — no frontend required.
🧩 What You'll Need
- ✅ OpenAPI Tools → https://openapitools.com
- ✅ Indian Stock Exchange API via RapidAPI
- ✅ Claude Desktop / Cursor / LangChain (MCP-compatible clients)
- ✅ Template Repo → https://github.com/kvssankar/openapitools-mcp
- ✅ One config file & one CLI command — that’s it!
🛠️ Step-by-Step: How It Works
1. 🧾 Pick Your API (Indian Stock Exchange API)
Use the free or paid version from RapidAPI:
👉 https://rapidapi.com/stock-api/api/nse-stock-market-india
Download its OpenAPI schema (swagger.json or .yaml).
2. ⚙️ Generate Your MCP Schema
Install OpenAPI Tools CLI:
npm install -g @openapitools/openapitools
🚀 Build Your Own API Research Assistant with OpenAPI Tools + MCP
So I tried out this cool tool I saw in a LinkedIn post — https://openapitools.com.
All you need is your API schema (OpenAPI/Swagger), and it automatically generates an MCP schema for you.
You can then drop it straight into Claude Desktop (or Cursor, LangChain, etc.) and instantly start chatting with your API 🤯
Super clean and insanely useful for research or rapid prototyping.
🔧 Example config.json
{
"server_name": "anthropic-mcp-server",
"host": "0.0.0.0",
"port": 8000,
"server_version": "0.1.0",
"tool_names": [],
"mode": "stdio",
"refresh_time_minutes": 1440,
"envs": {
"x_api_key": "sk-live-rAETxrBOMAYuKVGxbmMgqQlfPoFGsCcu7csbO1PJ"
}
}