DalalOS
About
MCP Server for Indian Stock Research
Details
- Author
- beyondnoww
- Categories
- Finance
Jump to
Setup
Install DalalOS in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/beyondnoww/DalalOS-Indian-Stock-Research
Follow the installation instructions in the repository README, then restart your MCP client.
DalalOS is a hosted Model Context Protocol (MCP) data layer for researching Indian NSE/BSE-listed companies with AI assistants and agents.
- Website:https://dalalos.in
- MCP endpoint:https://mcp.dalalos.in/mcp
- Connection guide:https://dalalos.in/connect
- Tool reference:https://dalalos.in/tools
- Data sources & freshness:https://dalalos.in/docs/data-sources-and-freshness
DalalOS exposes structured Indian-market research data to MCP-compatible clients, including:
- company and security search;
- end-of-day quotes and price history;
- company financial statements and mechanically-computed ratios;
- peer and sector comparison data;
- shareholding and promoter-pledge data;
- corporate actions, results, filings and disclosed events;
- screening, indices and market context;
- official macro/reference datasets used for research context; and
- an account-scoped DalalOS watchlist.
Data is sourced from official and public Indian-market sources such as NSE archives, BSE official interfaces and exchange filings, SEBI-mandated BSE-XBRL filings, and the named official public-sector publisher for supported macro/reference datasets.
- Not real-time:quote-style stock-market data is end-of-day, not a live tick or order-book feed.
- Research, not execution:DalalOS is not a broker and does not place market orders or execute trades.
- No investment advice:DalalOS returns sourced facts and mechanically-computed measures, not buy/sell calls, target prices or investment recommendations.
- Read/write scope:market-data research tools are read-only. The explicit write exception is the caller's own DalalOS watchlist, where authenticated users can add or remove symbols.
- Missing data stays explicit:unsupported, unavailable or stale coverage is surfaced rather than replaced with invented values.
Use the hosted streamable-HTTP endpoint:
OAuth is the preferred authentication path for clients that support it. API-key Bearer authentication is available as a fallback for compatible clients that require it.
It intentionally doesnotpublish tool implementation modules, input-schema hashes, REST mappings, storage/cache details, source-adapter logic, refresh mechanics, deployment information, credentials, or other backend internals.
Deprecated compatibility aliases remain in the registered-name list but are excluded frompreferred_tool_count, so directories and product surfaces can avoid inflating capability counts with old aliases.
The public registry manifest isserver.json. DalalOS already has an official MCP Registry identity under:
That existing identity is intentionally preserved so the hosted endpoint has one canonical Registry record. Registry metadata changes must be published using credentials authorized for that existing namespace; this public repository does not store those credentials.
This repository is thepublic project, integration and discovery surfacefor DalalOS. It exists so users, MCP registries, AI-tool directories and open-source ecosystem lists have a stable public GitHub reference for the hosted service.
It intentionally doesnotcontain the DalalOS backend implementation. In particular, this repository does not publish internal ingestion logic, database/cache schemas, source-adapter code, deployment topology, credentials, private operational tooling, private issue/PR history, or unpublished architecture.
Public files in this repository are limited to integration metadata, connection documentation, public capability/provenance descriptions and safe usage examples.
- server.json— MCP Registry metadata for the hosted server.
- capabilities.json— sanitized machine-readable capability names/read-write/deprecation contract.
- docs/CONNECT.md— connection and authentication notes.
- docs/DATA_SOURCES.md— provenance and freshness contract.
- docs/DIRECTORY_LISTING.md— canonical copy for MCP directories, AI-tool catalogs and curated resource lists.
- docs/OPENAI_PLUGIN_SUBMISSION.md— public-safe OpenAI Plugin listing/review preparation pack, including starter prompts and positive/negative capability tests.
- examples/PROMPTS.md— example research prompts and capability-boundary examples.
- CONTRIBUTING.md— public contribution and implementation-leak guardrails.
- SECURITY.md— responsible security reporting guidance.
- Privacy:https://dalalos.in/privacy
- Terms:https://dalalos.in/terms
DalalOS is not affiliated with or endorsed by NSE, BSE, SEBI, OpenAI, Anthropic, Cursor, or another AI-client vendor unless explicitly stated otherwise by that party.
Bridge Town is an MCP-native, git-versioned financial modeling platform for FP&A teams and finance leaders. AI agents use Bridge Town tools to create projects, write Python model files, run models in isolated cloud sandboxes, query data, write outputs to Google Sheets, create dashboards, branch scenarios, and collaborate with teammates.
The Capital.com MCP Server lets your AI assistant talk to your trading account directly. Market data, position checks, trade previews – all in plain language, without leaving your AI tool.
Coinrule Agentic Trading MCP enables investors to create, backtest, execute, and manage trading agents through natural language across stocks, crypto and ETFs
Invest with Claude and other AI assistants
Australian Consumer Data Right Product Data
Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp
Cross-border debt collection from your AI assistant: check cases, get pricing, submit new cases.
Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.
Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
