MCP SERVER

The Indian stock market MCP server

DalalOS is an Indian stock market MCP server: the Indian stock market layer for AI-powered stock research. It connects AI assistants and agents to official NSE and BSE data through the Model Context Protocol, so AI-savvy Indian investors can explore fundamentals, compare companies and understand market context with their AI tools.

It is hostable, read-only, and built to be plugged into any MCP client — Claude, ChatGPT-style agents, Cursor and other AI agents.

20+
Read-only MCP tools
~5,000
NSE & BSE companies
3
Official data sources
0
Buy/sell calls or advice

What is an MCP server?

The Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools. An MCP server exposes those tools; DalalOS exposes Indian stock-market data as read-only tools your assistant can call and reason over.

What the server does

The Model Context Protocol is an open way for AI assistants to call external tools. An Indian stock market MCP server like DalalOS packages NSE/BSE market data as those tools. When you connect it, your assistant can answer questions about Indian equities using live, sourced figures instead of stale memory.

It exposes 20+ read-only tools over streamable HTTP. Every response arrives in one consistent envelope — status, data, source and a freshness timestamp — so both humans and agents always know where a number came from and how current it is.

Capabilities & data coverage

DalalOS data coverage by capability
CapabilityWhat it returnsSource
Quotes & pricesEnd-of-day quotes, prices and 52-week rangeNSE archives
Financials & ratiosPE, PB, ROE, ROCE, D/E — quarterly & annualSEBI BSE-XBRL
Company profilesProfiles and peer comparisonNSE / BSE
ShareholdingShareholding patterns and promoter pledge trendsSEBI BSE-XBRL
Corporate actionsDividends, corporate actions and stock eventsBSE official APIs
Screening & sectorsScreening, sector overviews, indices, constituents, upcoming resultsNSE / BSE

Stock search spans roughly 5,000 NSE and BSE companies, and every response carries a data freshness timestamp so you always know how current a number is.

Where the data comes from

Official and public sources only: NSE archives (end-of-day bhavcopy), BSE official APIs and SEBI BSE-XBRL filings. There is no scraped third-party data, and the server returns raw data and mechanically-computed ratios only — no verdicts, no target prices, no buy/sell calls. It is not a real-time exchange feed.

How it works

01

Host or connect

Point any MCP client at the streamable HTTP endpoint.

02

Call read-only tools

Your assistant invokes the right tool for each question.

03

Reason over sourced data

Answers cite their source and freshness; you decide what to do.

Add the MCP config

Connecting is a single config block. Use the server key dalal-os and the streamable HTTP endpoint.

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

Example prompts

EXAMPLE PROMPTS

  • What is the 52-week range for Sun Pharma, and its latest end-of-day price?
  • Give me five-year revenue, ROCE and D/E for Asian Paints.
  • Compare the largest cement makers on PE, PB and ROE.
  • Which Nifty 500 stocks have promoter pledge above zero and rising?
  • List upcoming results due this week with their dates.

Ready to connect a specific client? See Claude, ChatGPT-style agents or Cursor and other AI tools.

FAQ

Common questions

What is an Indian stock market MCP server?

It is a server that speaks the Model Context Protocol and exposes Indian (NSE/BSE) stock market data as tools an AI assistant can call. DalalOS is one such server, offering 20+ read-only tools over streamable HTTP.

What data does DalalOS cover?

Stock search; end-of-day quotes, prices and 52-week ranges; financials and ratios (PE, PB, ROE, ROCE, D/E, quarterly and annual); company profiles; peer comparison; shareholding and promoter pledge trends; dividends and corporate actions; screening; sector overviews; indices and constituents; and upcoming results — across roughly 5,000 NSE and BSE companies.

Where does the data come from?

Official and public sources only: NSE archives (end-of-day bhavcopy), BSE official APIs and SEBI BSE-XBRL filings. No scraped vendor data.

Is it investment advice?

No. DalalOS returns raw data and mechanically-computed ratios only — no verdicts, target prices or buy/sell calls. Verify data and make investment decisions independently.

Connect your AI to Indian stock market data

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

Be the first in line · no spam, just launch news

KEEP EXPLORING