Skip to main content

Indian Stock Research MCP server powered by Screener.in

Project description

screener-mcp — Indian Stock Research for Claude

Turn Claude into a personal Indian equity analyst powered by live Screener.in data.

Ask Claude naturally — it fetches real financial data and reasons over it like a seasoned analyst.


Demo

Screenshot / GIF coming soon. Try it yourself and see!


What you can ask

"Compare ITC and HUL"
"Find chemical stocks with low debt and strong growth"
"Explain Jyothy Labs like I'm a beginner"
"What are the red flags in Asian Paints?"
"Find hidden gems below ₹5000 crore market cap"
"Show me TCS quarterly results for last 2 years"
"What is the promoter holding trend for Titan?"
"Find companies with improving ROCE over 5 years"
"Which companies benefit from EV adoption?"
"Give me businesses with 15%+ profit growth and low debt"

Quick install (recommended)

If you have uv installed (pip install uv or brew install uv):

claude mcp add screener -s user -- uvx screener-mcp

That's it. No cloning, no venv setup — uvx handles everything automatically.

Don't have uv? Install it: pip install uv or brew install uv


Manual install (alternative)

git clone https://github.com/LogeshR15/screener-mcp
cd screener-mcp

python3.11 -m venv .venv
source .venv/bin/activate        # Windows: .venv\Scripts\activate
pip install httpx beautifulsoup4 lxml "mcp[cli]"

claude mcp add screener -s user -- \
  $(pwd)/.venv/bin/python3.11 \
  $(pwd)/run_server.py

Setup credentials (required for stock screening)

Company data (financials, ratios, shareholding) works without login. Stock screening requires a free Screener.in account.

1. Register free at screener.in/register

2. Add to your shell profile (~/.zshrc or ~/.bashrc):

export SCREENER_USERNAME="your@email.com"
export SCREENER_PASSWORD="yourpassword"

3. Reload your shell (source ~/.zshrc) and restart Claude Code.


Verify it's connected

claude mcp list
# screener  stdio  ✓ Connected

Then ask Claude: "Search for Asian Paints" — you should get results.


Tools available

Tool What it does Login needed?
search_company Find company by name or symbol No
get_company_overview Key ratios, price, about No
get_financials P&L / Balance Sheet / Cash Flow / Ratios No
get_quarterly_results Last 8 quarters of results No
get_shareholding_pattern Promoter/FII/DII holding trends No
get_peer_comparison Peer comparison table No
compare_companies Side-by-side multi-company comparison No
get_full_analysis All data combined for deep analysis No
analyze_red_flags Structured red flag detection No
explain_for_beginners Plain-language company explainer No
screen_stocks Custom Screener.in query Yes
screen_by_theme Pre-built thematic screens Yes
list_investment_themes Show all available themes No

Pre-built themes

undervalued_small_cap     — Small caps with ROCE > 15%, low debt
high_roce_low_debt        — ROCE > 20%, debt to equity < 0.3
compounders               — 15%+ growth: revenue, profit, ROE, ROCE
turnaround                — Strong recent profit recovery
rising_profit_falling_price — Improving profits, compressed PE
hidden_gems               — Small cap, high ROCE, strong growth
dividend_aristocrats      — Consistent dividends with quality financials
qarp                      — Quality at reasonable price
micro_cap_growth          — High-growth micro caps < ₹1000 Cr
ev_theme                  — EV & auto ancillary growth companies
chemicals                 — Specialty chemicals with strong fundamentals
defense                   — Defense sector with revenue momentum
railways                  — Railway infra/equipment companies
renewable_energy          — Renewable energy sector

Architecture

screener-mcp/
├── run_server.py                  # Entry point
└── src/screener_mcp/
    ├── server.py                  # FastMCP server — tool definitions
    ├── client.py                  # HTTP client (auth, rate limiting)
    ├── parsers/
    │   ├── company.py             # Parse company HTML pages
    │   └── screener.py            # Parse screener results
    └── tools/
        ├── company_tools.py       # Company data tools
        ├── screening_tools.py     # Stock screening tools
        └── analysis_tools.py     # Deep analysis tools

Data source & limitations

All data comes from Screener.in — India's most popular stock research platform covering BSE and NSE listed companies with 10+ years of financial history.

  • Financial data is updated quarterly (lags by ~1 quarter)
  • This is a research tool — not financial advice
  • Always verify critical data directly on Screener.in

Contributing

See CONTRIBUTING.md — adding a new tool takes ~10 minutes.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

screener_mcp-0.1.0.tar.gz (23.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

screener_mcp-0.1.0-py3-none-any.whl (25.4 kB view details)

Uploaded Python 3

File details

Details for the file screener_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: screener_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 23.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for screener_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 507ca71a054b625c243c1fdfe93a41143964c984a76a4d78b7fd9858312cc681
MD5 d56e55ad104344a29a10cd2c28410af7
BLAKE2b-256 ef3c1473f9c01b65a3b8864b0255ab393a8ea81bd07f4cb28b001e43e31d0e8c

See more details on using hashes here.

File details

Details for the file screener_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: screener_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 25.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for screener_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 48e94f3517dc603cd6007b34c73eec73b5809463bf7db9a9d76d064819e15d16
MD5 825410f9573800927f68abab719c7877
BLAKE2b-256 df82bbeecbd6279b23bc7e27d9d86df2440e5c02cc1213e4cd9c14eff05f6328

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page