InvestSights Indian Stock Research MCP
About
Research-grade Indian stock data (NSE/BSE) — fundamentals, forensic accounting scores, DCF valuation, screening, prices & news for 6000+ stocks.
Details
- Author
- InvestSights
- Downloads
- 175
- Transport
- SSE
- Categories
- Finance, Other
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
InvestSights Indian Stock Research MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
{
"mcpServers": {
"investsights-indian-stock-research-mcp": {
"type": "http",
"url": "https://investsights.in/api/v2/mcp-public/mcp"
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"investsights indian stock research mcp": {
"investsights-indian-stock-research-mcp": {
"type": "http",
"url": "https://investsights.in/api/v2/mcp-public/mcp"
}
}
}
}McpServers
{
"investsights-indian-stock-research-mcp": {
"type": "http",
"url": "https://investsights.in/api/v2/mcp-public/mcp"
}
}Research-grade Indian stock data (NSE/BSE) — fundamentals, forensic accounting scores, DCF valuation, screening, prices & news for 6000+ stocks.
InvestSights — Indian Stock Research MCP Server
The Model Context Protocol server for deep Indian stock research — fundamentals, forensic accounting scores, DCF valuation, screening, prices, technicals and news for 6,000+ NSE & BSE stocks, from Claude, ChatGPT, Perplexity, Cursor & any AI assistant.
Documentation•Quick Start•Tools•Example Prompts•npm
InvestSights MCP is aModel Context Protocolserver that connects AI assistants toresearch-grade Indian stock market data— the same engine that powersinvestsights.in.
Where most market servers stop at quotes and screens, InvestSights adds a research layer:forensic accounting scores(Piotroski F, Beneish M, Altman Z — with bank-aware CAMELS handling),multi-stage DCF + relative valuation,analyst consensus, shareholding patterns and curated news — for 6,000+ NSE/BSE companies.
Compatible with:Claude.ai, Claude Desktop, Claude Code, ChatGPT, Perplexity, Cursor, Windsurf, VS Code (Copilot), Kiro, Zed, Codex, Gemini, Grok, OpenCode, and any MCP-compatible client.
Option 1: Remote MCP with OAuth (claude.ai, ChatGPT, Perplexity, Grok)
Add this URL as a custom connector in your AI chat app:
https://investsights.in/api/v2/mcp-public/mcp
Option 2: Remote MCP with Token (Claude Code, VS Code, Kiro, Zed)
For code editors that support URL-based MCP servers with custom headers:
- Get a free key atinvestsights.in/account/connected-apps
- Add to your MCP config:
{ "mcpServers": { "investsights": { "type": "url", "url": "https://investsights.in/api/v2/mcp-public/mcp", "headers": { "Authorization": "Bearer usk_YOUR_KEY_HERE" } } } }
URL-only client (no header support)? Use the key-in-URL form:https://investsights.in/api/v2/mcp-public/usk_YOUR_KEY_HERE/mcp
Option 3: Local MCP via npm (Cursor, Windsurf, Claude Desktop, Codex, Gemini CLI)
For stdio-based MCP clients. No cloning or building — runs vianpx:
- Get a free key atinvestsights.in/account/connected-apps
- Add to your MCP config:
{ "mcpServers": { "investsights": { "command": "npx", "args": ["-y", "investsights-mcp"], "env": { "INVESTSIGHTS_TOKEN": "usk_YOUR_KEY_HERE" } } } }
Node.js 18+required for the local option. Runnode --versionto check.
┌─────────────────┐ stdio (JSON-RPC) ┌───────────────────┐ HTTPS ┌─────────────────────┐ │ AI Assistant │ ◄──────────────────► │ investsights-mcp │ ◄───────────► │ investsights.in │ │ (Claude, etc.) │ │ (npm package) │ │ (research backend) │ └─────────────────┘ └───────────────────┘ └─────────────────────┘
The npm package is a lightweight stdio bridge (~250 lines,zero runtime dependencies). It:
- Reads JSON-RPC from stdin, forwards to the remote InvestSights MCP server, writes responses to stdout
- Auto-detects framing:Content-Length(VS Code, Claude Desktop) or newline-delimited JSON (Claude Code, Kiro)
- Authenticates every request with your personal key as a Bearer token
- Handles SSE responses from the remote server
All tools and their logic run on the remote server — the npm package is just the transport layer.
Create and revoke keys anytime atinvestsights.in/account/connected-apps. Same free limits across every method.
A curated pack of fast, read-only research tools — your AI picks the right one automatically.
Enterprise:the full 40+ tool catalog — GraphRAG document intelligence, earnings-call analysis, corporate-governance graphs, superstar-investor tracking, portfolio analytics — is available with dedicated keys and custom limits. Contactconnect@investsights.in.
"Compare HDFC Bank vs ICICI Bank — profit growth, ROE, valuation and shareholding trends right now" "Pull TCS fundamentals and shareholding — is FII holding rising or falling?"
"Run a forensic accounting check on Suzlon — Piotroski, Beneish, Altman. Any red flags?" "Which looks financially healthier on forensic scores: Zomato or Swiggy?"
"What does a DCF say about TCS at today's price? Show bull, base and bear scenarios with the key assumptions"
"Find stocks with ROE > 18%, low debt, and RSI under 40 — oversold quality names" "Screen mid-caps with improving margins and P/E below 20 — top 15"
"Today's Indian market overview — index moves, strongest sector, and this week's earnings calendar"
Higher limits and the full tool catalog are available for teams and platforms —connect@investsights.in.
SetINVESTSIGHTS_DEBUG=1for detailed logging to stderr.
- investsights.in— Web platform
- investsights.in/mcp— MCP documentation & setup guide
- investsights.in/docs— Full developer & tool reference
- npm: investsights-mcp— npm package
InvestSights is an analytics platform and isnot SEBI-registeredas a Research Analyst or Investment Adviser. Every tool isread-onlyand returns data, ratios and scores — never buy/sell recommendations, target prices or personalised advice. All output is educational; consult a SEBI-registered adviser before investing. Investments in securities markets are subject to market risks.
Issues and pull requests are welcome for the bridge itself. For bugs, include the error message and your MCP client name/version.
Built byInvestSights— a product ofSocialCoffee DigiTech Pvt Ltd
akta.pro MCP connects Claude, ChatGPT, Cursor, VS Code, and other MCP clients to enterprise-grade private company data and real-time news signals. 20M+ entity-resolved companies, 70+ data points each, 30K+ sub-sectors monitored, and ~80% news noise filtered — pay-as-you-go.
Free keyless gapper scanner — the Warrior Trading "5 pillars" low-float momentum screen. Finds cheap small-cap stocks gapping up hard on high relative volume with a news catalyst; auto-picks premarket (4:00–9:30 ET) or after-hours (16:00–20:00 ET) tape. No API key required.
Read-only financial data for market, macro, news, company, and congressional research.
US market snapshot, stock fundamentals, prices, statements, news and analyst views
Objective-driven deep research paid per request via MPP - free daily quick search (news/arXiv), quote-first paid cloud-browser research with cross-source reports. MCP Streamable HTTP, no API key.
Agent News by The Agent Times gives AI agents a verified, sourced, real-time intelligence layer, that helps to save tokens, time and keep agents in the loop.
About Free multi-engine MCP search server — 8 free engines (DDG, Sogou, Bing, Baidu, Wikipedia, Startpage, Yandex, Mojeek), waterfall progressive search, multi-source verification, content enrichment, news search, language auto-detection, rate limit exposure. Zero API keys needed. Self-hostable.
Hosted MCP server for the APITube News API: search articles from 500,000+ sources in 60+ languages, filtered by sentiment, entities, topics and source quality.
A search engine for AI applications, providing world knowledge from web pages and various content sources like weather, news, and images.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
