Investo 📈

An AI investment-analysis agent you run from Claude or Cursor.

Give Investo a company name — Indian (NSE/BSE) or global — and it gathers public financial data and produces a full analysis: what the company does, its financials & ratios, a competitor comparison, DCF intrinsic value, economic moat, risks, management, recent news, SWOT seeds, and a 0–100 investment rating.

Investo is a Model Context Protocol (MCP) server. It exposes tools to an AI client (Claude Code, Claude Desktop, Cursor); the client calls those tools and writes the analysis narrative grounded in the structured data Investo returns.

Primary focus: Indian companies listed on NSE (.NS) and BSE (.BO). US/global companies are supported too.

---

What it produces

For any company, Investo supplies the evidence for:

1. Domain / sector — what the business does and its sub-domains.
2. Financials & ratios — income statement, balance sheet, cash flow + valuation, profitability, leverage, liquidity, growth, cash-flow ratios.
3. Competitor analysis — auto-compares against sector peers (e.g. Infosys → TCS, Wipro, HCL, Tech Mahindra, LTIMindtree).
4. Industry intelligence — sub-domains, demand drivers, CAGR, risks.
5. News analysis — recent headlines categorized (earnings, M&A, management, legal, product/AI).
6. Management analysis — executives, promoter/insider holding, capital allocation.
7. DCF valuation — intrinsic value/share, margin of safety, expected return.
8. Economic moat — brand / network / cost / scale / switching-cost signals.
9. Risk analysis — debt, currency, concentration, regulation, tech obsolescence.
10. Rating out of 100 — a balanced 11-bucket score with per-bucket rationale.

Rating buckets (out of 100)

Growth	Profitability	Cash Flow	Debt	Valuation	Moat	Management	Industry	Innovation	Risk	ESG*
15	15	10	10	15	10	10	5	5	5	5*

*ESG is optional; when unavailable the remaining buckets renormalize to 100.

---

Install

Requires Python 3.10+.

git clone https://github.com/YashvantHange/Investo
cd Investo
python -m venv .venv
# Windows: .venv\Scripts\activate   |   macOS/Linux: source .venv/bin/activate
pip install -e .

No API keys are required — Investo works out of the box using free Yahoo Finance data and Google/Yahoo news. Optional keys (Alpha Vantage / FMP / Finnhub) enable richer/fallback data; copy .env.example to .env and fill in any you have.

---

Try it from the command line

investo analyze "Infosys"
investo analyze "Reliance Industries"
investo analyze "Tata Motors"
investo analyze AAPL
investo search "tata motors"

Use it from Claude Code / Cursor

Do the one-time setup (creates the venv the launcher looks for):

python -m venv .venv
.venv\Scripts\pip install -e .     # macOS/Linux: .venv/bin/pip install -e .

Claude Code — this repo ships a project-scoped .mcp.json that runs python scripts/mcp_launcher.py. No paths to edit — the launcher finds the project's .venv itself and works on Windows/macOS/Linux. Opening the folder in Claude Code offers to load the investo server (approve on first use); the included CLAUDE.md makes the agent introduce itself as Investo.

Cursor — copy examples/cursor_mcp.json to .cursor/mcp.json (same portable launcher).

Claude Desktop — it doesn't run from the project folder, so give the absolute path to scripts/mcp_launcher.py (see examples/claude_desktop_config.json). You still don't hardcode a Python path — the launcher locates the venv for you.

Then ask: "Analyse Infosys", "Compare HDFC Bank with its peers", "What's the DCF value of Reliance?"

How the launcher works: scripts/mcp_launcher.py is a tiny standard-library script. When a client runs it with any python, it re-launches the server inside the project's .venv (or uses the current interpreter if investo is already installed there). That's why the committed config needs no machine-specific paths.

---

MCP tools

Tool	Purpose
search_company	Resolve a name to an NSE/BSE/global ticker
get_company_profile	Sector, business summary, market cap, executives
get_financials	Income statement / balance sheet / cash flow
get_key_ratios	Valuation, profitability, leverage, growth, cash-flow ratios
compare_peers	Competitor comparison table
get_industry_intelligence	Sub-domains, demand drivers, CAGR, risks
get_news	Categorized recent headlines
get_management	Executives, holdings, capital allocation
dcf_valuation	Intrinsic value, margin of safety, expected return
moat_assessment	Economic-moat signals + heuristic score
risk_assessment	Risk signals + heuristic score
score_company	0–100 composite rating
analyze_company	Everything above bundled into one report
get_sec_facts	SEC EDGAR cross-check (US/ADR only)

---

Data & limitations

Investo uses public data and is for research/education only — not investment advice.

• Yahoo Finance is the primary source (covers NSE/BSE + global). It can rate-limit or omit fields; tools degrade gracefully and return what's available.
• Promoter/insider shareholding for NSE/BSE has no clean free API — this is best-effort in v1 and often unavailable for Indian names (enhance later via a keyed API / BSE shareholding pattern).
• Industry CAGR / market share are curated/estimated, not live.
• Peer lists start curated for major Indian sectors and are extensible via data/peers.yaml.

---

License

MIT