<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Rony Varghese on Medium]]></title>
        <description><![CDATA[Stories by Rony Varghese on Medium]]></description>
        <link>https://medium.com/@ronyv89?source=rss-264a5aa9745c------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*bnjB12rkVgBEnL3o.jpg</url>
            <title>Stories by Rony Varghese on Medium</title>
            <link>https://medium.com/@ronyv89?source=rss-264a5aa9745c------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 21:09:45 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@ronyv89/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[screener-mcp: Query Indian Stock Fundamentals Directly in Your AI Conversations]]></title>
            <link>https://medium.com/@ronyv89/screener-mcp-query-indian-stock-fundamentals-directly-in-your-ai-conversations-cc5fa9350993?source=rss-264a5aa9745c------2</link>
            <guid isPermaLink="false">https://medium.com/p/cc5fa9350993</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[stock-screener]]></category>
            <category><![CDATA[claude]]></category>
            <category><![CDATA[stock-market]]></category>
            <category><![CDATA[mcp-server]]></category>
            <dc:creator><![CDATA[Rony Varghese]]></dc:creator>
            <pubDate>Wed, 01 Apr 2026 08:48:29 GMT</pubDate>
            <atom:updated>2026-04-01T08:48:29.791Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*fVK4msjwNFnkSkoLRxSOwA.png" /></figure><p>If you’ve ever wished you could just ask your AI assistant “What are the key financial ratios for Reliance Industries?” and get a real, structured answer — without copy-pasting data from multiple browser tabs — you’re going to love <strong>screener-mcp.</strong></p><p><strong>screener-mcp</strong> is an open-source Model Context Protocol (MCP) server that plugs directly into Claude Desktop (or any MCP-compatible AI client) and gives it live access to financial data for Indian listed companies from screener.in. No API key. No complicated setup. Just clone, build, and start asking your AI about stocks in plain English.</p><h3>What is MCP?</h3><p>The Model Context Protocol (MCP) is an open standard introduced by Anthropic that allows AI assistants like Claude to connect with external tools and data sources in a structured, standardized way. Think of it as a USB-C port for AI — instead of building bespoke integrations for every tool, developers implement one protocol and any compatible AI client can use it immediately.</p><p><strong>screener-mcp</strong> is one such server. It bridges the gap between your AI assistant and screener.in — India’s most popular platform for equity research — so you can conduct meaningful stock analysis right inside your chat interface.</p><h3>What Can screener-mcp Do?</h3><p>The server exposes two primary MCP tools that Claude (or any compatible client) can call on demand:</p><blockquote><strong><em>search_company</em></strong> — Search for any Indian listed company by name or ticker symbol. Whether you type “Tata” or “TCS” or “RELIANCE”, the tool finds the right entity on screener.in.</blockquote><blockquote><strong><em>get_company_data</em></strong> — Fetch detailed financial data for a company. You can request all data at once or pass a specific fields array to retrieve only what you need, keeping responses fast and concise.</blockquote><p>The available data fields you can pull include: <em>ratios (Market Cap, P/E, P/B, ROE, ROCE, etc.), quarterly_results (quarterly revenue, profit, and EPS), profit_loss (annual P&amp;L statement), balance_sheet (annual balance sheet), cash_flow (annual cash flow statement), shareholding (promoter/FII/DII shareholding pattern), and peers (peer comparison table).</em> Both consolidated and standalone financials are supported.</p><h3>Installation</h3><p>Getting started is straightforward. You’ll need Node.js 18 or higher and npm installed on your machine. Then run the following in your terminal:</p><blockquote>git clone <a href="https://github.com/ronyv89/screener-mcp">https://github.com/ronyv89/screener-mcp</a></blockquote><blockquote>cd screener-mcp</blockquote><blockquote>npm install</blockquote><blockquote>npm run build</blockquote><p>That’s it — no API keys to obtain, no authentication to configure. The server pulls data directly from screener.in’s public pages.</p><h3>Connecting to Claude Desktop</h3><p>To wire it up to Claude Desktop, open your Claude Desktop config file. On macOS this lives at ~/Library/Application Support/Claude/claude_desktop_config.json, and on Windows at %APPDATA%\Claude\claude_desktop_config.json. Add the <strong>screener-mcp</strong> server entry under the mcpServers key:</p><p>{ “mcpServers”: { “screener”: { “command”: “node”, “args”: [“/absolute/path/to/screener-mcp/dist/index.js”] } } }</p><p>Replace /absolute/path/to/screener-mcp with the actual path on your system, save the file, and restart Claude Desktop. That’s all it takes.</p><h4>Using with Claude Code</h4><p>If you’re a Claude Code user, registering the server is even simpler. After building, run:</p><blockquote>claude mcp add screener — node “/absolute/path/to/screener-mcp/dist/index.js”</blockquote><h3>Example Prompts You Can Ask</h3><p>Once you’ve configured the server, your AI conversations become a full-fledged stock research terminal. Here are a few things you can ask Claude directly:</p><p>“What are the key financial ratios for Reliance Industries?”</p><p>“Show me the quarterly results for TCS for the last year.”</p><p>“Compare HDFC Bank with its peers.</p><p>“Get Infosys’s balance sheet for the last 5 years.”</p><p>“Search for companies with the name ‘Tata’ and show me their promoter shareholding.”</p><p>Claude will call the appropriate <strong>screener-mcp</strong> tools under the hood, fetch the data, and reason over it — so instead of just retrieving raw numbers, you get thoughtful analysis and explanations alongside the data.</p><h3>Under the Hood</h3><p><strong>screener-mcp</strong> is built with TypeScript (targeting ES2022 modules) and uses three core libraries: the official @modelcontextprotocol/sdk to implement the MCP server framework, cheerio for HTML parsing and web scraping of screener.in’s public pages, and Node’s native fetch API for HTTP requests. The result is a lean, dependency-light server with no heavy runtime requirements.</p><p>A built-in 5-minute cache ensures that repeated queries for the same company are served instantly without hammering screener.in’s servers. Data is sourced from BSE/NSE filings as aggregated by screener.in, meaning it reflects the same authoritative data that equity analysts rely on every day.</p><h3>Why This Matters</h3><p>The Indian retail investing space has grown explosively over the last few years, and tools like screener.in have become indispensable for individual investors doing their own research. But there’s still friction — you look up ratios on one tab, pull up a peer comparison in another, copy numbers into a spreadsheet, and only then can you start reasoning about them.</p><p><strong>screener-mcp</strong> collapses that workflow into a single conversation. You describe what you want to understand about a company, and Claude handles the fetching, aggregation, and analysis in one shot. It’s a meaningful productivity boost for retail investors, finance students, and anyone who follows the Indian markets.</p><h3>Get Started</h3><p>The project is open source and available on GitHub at <a href="https://github.com/ronyv89/screener-mcp.">https://github.com/ronyv89/screener-mcp.</a> Contributions, bug reports, and feature requests are welcome. If you find <strong>screener-mcp</strong> useful, give the repository a star — it helps the project get discovered by others in the community.</p><p>Happy investing — and happy prompting.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=cc5fa9350993" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>