Use ChatGPT, Cursor & other AI tools for Indian stock research

Why connect your AI tool to DalalOS

Large language models reason well but store data poorly. Ask a raw ChatGPT-style agent for a mid-cap company's latest ROCE and it may guess. DalalOS gives the agent 59 current MCP capabilities over streamable HTTP, sourced from official NSE archives, BSE official interfaces and SEBI-mandated BSE-XBRL filings across thousands of companies. Market figures are read from cache; filing tools can queue processing and use on-demand quota. The 2 account-scoped writes only add or remove symbols from your DalalOS watchlist.

You get AI-assisted stock research on sourced data. The reasoning comes from you and the model. DalalOS involves no scraping and bakes in no verdicts. Because it speaks MCP, one endpoint serves Claude, ChatGPT-style agents, Cursor, Perplexity and other MCP-capable AI agents.

Connect ChatGPT with the DalalOS plugin

Use the published plugin: open DalalOS in ChatGPT, select Install plugin, and sign in to DalalOS when prompted (Google, or a code we email you). You create no key and paste no URL. The plugin is published for ChatGPT users in India; availability can vary by plan or workspace.

Manual setup if the plugin is not available to you

If the plugin page does not open or your region or plan does not offer it, add the server yourself. We verified this flow with ChatGPT on the web and a personal Plus account. In ChatGPT, open Plugins, choose Create Plugin, and enter the following details. Interface labels and availability can vary by plan or workspace. ChatGPT does not use an mcpServers JSON file for this flow.

For a first test, ask: “Use DalalOS to fetch the latest available quote and company profile for Reliance Industries. Tell me which DalalOS tools you called, the source of the data, and its freshness date. Do not use web search.”

A successful response names the tools it called and includes source and freshness information. Prices are end-of-day, and DalalOS is not a real-time exchange feed. If ChatGPT rejects the server URL, confirm that it matches https://mcp.dalalos.in/mcp, including the /mcp path.

Connect Cursor and other OAuth-capable clients

Cursor and other clients that support remote MCP OAuth can use the same hosted endpoint. Add https://mcp.dalalos.in/mcp as a remote MCP server, choose OAuth when prompted, and complete the browser sign-in. Config schemas differ between clients, so follow your client's own configuration format and documentation.

API-key fallback for config-based clients

Use an API key only when a client cannot complete OAuth or requires a Bearer header. Sign in to DalalOS, open Dashboard → API keys, and create a key. The example below applies to clients that accept the mcpServers configuration shape.

{
  "mcpServers": {
    "dalal-os": {
      "url": "https://mcp.dalalos.in/mcp",
      "headers": {
        "Authorization": "Bearer <your-isk_live_-key>"
      }
    }
  }
}

Replace <your-isk_live_-key> with the key you copied. Treat it like a password: anyone holding it can query DalalOS on your behalf. Never commit it to a repository or share it in a screenshot.

Generic OAuth configuration

For clients that accept the standard mcpServers shape and handle OAuth, use this keyless configuration. Do not add an API key unless the client asks for one.

{
  "mcpServers": {
    "dalal-os": {
      "url": "https://mcp.dalalos.in/mcp"
    }
  }
}

Example prompts

For developers and builders

Market-data responses come back in one consistent envelope (status, data, source, freshness), so you can compose tool calls into personal AI agents for Indian stock research, dashboards or research scripts. Drive them from Cursor, a CLI agent or your own code. Research capabilities place no trades. The account-scoped watchlist surface is your own DalalOS watchlist: authenticated add and remove actions save symbols and do not touch a brokerage account.

• Chain tools (search → quote → financials → peers) inside an agent loop.
• Build repeatable research workflows that cite data freshness.
• Keep the investor framing: the output is research data and contains no advice.

Good practices for AI-assisted research

• Ask the agent to state the data freshness timestamp it used.
• Treat ratios as inputs to your own analysis. DalalOS computes them from fixed formulas and offers no opinion.
• Cross-check anything important against the primary filing before acting on it.
• Remember that the data is end-of-day and excludes intraday ticks.

For next steps, see using ChatGPT for Indian stock analysis or the broader guide to Indian stock market data for AI agents.