screener-mcp
Exposes Screener.in data for Indian stocks (NSE/BSE) — fundamentals, financial statements, peers, and price/EPS time-series — as tools any MCP client can call.
README
screener-mcp
An MCP server exposing Screener.in data for Indian stocks (NSE/BSE) — fundamentals, financial statements, peers, and price/EPS time-series — as tools any MCP client (Claude, etc.) can call.
Screener.in is server-rendered (Django), so most data comes from a single HTML GET; the chart tool uses Screener's JSON chart API.
Tools
| Tool | Args | Returns |
|---|---|---|
get_fundamentals |
symbol |
Key ratio cards (P/E, P/B, ROE, ROCE, Market Cap, Book Value, Dividend Yield, etc.), pros/cons, about |
get_financials |
symbol |
Statement tables: Quarterly Results, P&L, Balance Sheet, Cash Flow, Ratios, Shareholding |
get_peers |
symbol |
Sector peer comparison table (CMP, P/E, Market Cap, Div Yield, NP, ROCE, sales growth) + sector median |
get_chart |
symbol, metric?, days? |
Time-series from the chart API. metric e.g. Price-DMA50-Volume, Price, Quarter Sales, EPS |
symbol is the NSE/BSE trading symbol, e.g. TCS, RELIANCE, MTARTECH.
Install & build
npm install
npm run build
Run
npm start # node dist/index.js (stdio transport)
# or during development:
npm run dev # tsx src/index.ts
Use from Claude Code
Add to your MCP config (.mcp.json or global), pointing at the built entry:
{
"mcpServers": {
"screener": {
"command": "node",
"args": ["/absolute/path/to/screener-mcp/dist/index.js"]
}
}
}
Then an agent can call get_fundamentals, get_financials, get_peers, get_chart.
How peers works
Screener lazy-loads the peer table from GET /api/company/{warehouseId}/peers/ — note
this uses a separate warehouse id (from data-warehouse-id on the page), not the
company id, and requires the X-Requested-With: XMLHttpRequest header. get_peers
resolves the warehouse id from the company page, fetches that fragment, and parses the
comparison table plus the sector-median row.
Testing
npm test
Tests run the parsers against a captured Screener HTML fixture (test/tcs.fixture.html),
so they are deterministic and don't hit the network.
Notes / etiquette
- Data is scraped from Screener.in for personal use. Respect their terms and don't hammer the site; cache results and rate-limit in your client.
- Selectors target Screener's current DOM; if Screener changes markup, the parsers
(
src/screener.ts) may need updating. The fixture test will catch regressions.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.