Use ChatGPT-style agents for Indian stock research

Why connect a ChatGPT-style agent to DalalOS

Large language models are strong reasoners but weak databases. Ask a raw ChatGPT-style agent for a mid-cap company's latest ROCE and it may guess. DalalOS fixes this by giving the agent 20+ read-only tools over streamable HTTP, sourced from official NSE archives, BSE official APIs and SEBI BSE-XBRL filings across roughly 5,000 companies.

The result: AI-assisted stock research where the data is real and the reasoning is yours plus the model's — with no scraping and no verdicts baked in.

How it works

Connect the server

Add the DalalOS MCP endpoint to your ChatGPT-style agent or MCP client.

Ask naturally

Pose a research question about an Indian company, sector or peer set.

Reason over data

The agent fetches official figures and explains them, citing freshness.

Add the MCP config

Many MCP clients use a JSON config very similar to Claude's. Use the server key dalal-os and the streamable HTTP endpoint. If your specific ChatGPT-style client uses a different connector UI, point it at the same endpoint.

claude_desktop_config.json

{
  "mcpServers": {
    "dalal-os": {
      "url": "https://indianstockdatamcp.duckdns.org/mcp"
    }
  }
}

Example prompts

EXAMPLE PROMPTS

Summarise Infosys' last four quarters of revenue and margins.
Compare Tata Motors and Mahindra & Mahindra on PE, PB, ROE and D/E.
What dividends, splits or results are coming up for ITC?
Screen for FMCG companies with ROCE above 25% and low debt-to-equity.
How has FII/promoter shareholding in a company changed over recent quarters?

Good practices for AI-assisted research

Ask the agent to state the data freshness timestamp it used, so you know how current the numbers are.
Treat ratios as inputs to your own analysis, not conclusions — DalalOS computes them mechanically and offers no opinion.
Cross-check anything important against the primary filing before acting on it.
Remember the data is end-of-day, not intraday.

Ready to put it to work? See using ChatGPT for Indian stock analysis or the broader guide to Indian stock market data for AI agents.

FAQ

Common questions

Can ChatGPT-style agents access Indian stock market data?

Yes — when you connect them to an MCP server like DalalOS. Any ChatGPT-style agent or AI client that supports the Model Context Protocol can call the read-only tools and pull official NSE/BSE data into its answers.

Is the data real-time?

No. Prices are end-of-day, financials arrive within the filing cycle, and shareholding updates quarterly. Each response is timestamped with its source. It is not a real-time exchange feed.

Does it give buy or sell recommendations?

No. DalalOS returns raw data and mechanically-computed ratios only. Your agent reasons over the numbers; you make every investment decision independently.

How is this different from asking ChatGPT directly?

Without a data connection, a model answers from memory, which can be stale or wrong for specific Indian tickers. Connected to DalalOS, the agent fetches current, sourced figures and shows where they came from.

Connect your AI to Indian stock market data

Join the waitlist and be first in line when your invite to DalalOS opens.

KEEP EXPLORING