ValuEdge Stock Research MCP Server

Use this when the user asks for a stock's ValuEdge financial history, profitability, growth, balance-sheet evidence, business quality, or data coverage. An optional history_limit requests up to 30 periods of selected metrics, current EPS consensus for at most three future fiscal years where present, quarterly P/E samples from existing monthly observations, and bounded source-native annual income, balance-sheet, and cash-flow statement rows where the existing snapshot contains them. EPS is not normalized and past estimate revisions are unavailable. Selected metric trends remain distinct from the full annual statement JSON. Do not infer a trade instruction.

Use this when the user asks for one stock's ValuEdge fair value, current price, margin of safety, valuation method, assumptions, confidence, or valuation risk. official_fair_value_source identifies the upstream model/component, while valuation_method_label describes headline composition, so a DCF source can accompany a blended headline. specialist_model.fair_value_blend is the optional source-provided equity-model breakdown and may be null when unavailable; blending_applied is independently reconciled from valid top-level canonical DCF/multiples values and weights. Do not use it for a user's private portfolio.

Use this when the authenticated user asks for their own portfolio concentration, sector or currency allocation, fair-value coverage, or risk context. Explain evidence and limitations without giving buy, sell, or hold instructions.

Use this when the user asks to compare two to six stocks on current price, canonical fair value, margin of safety, confidence, valuation risk, and fair-value coverage. This tool compares valuation only; use get_stock_fundamentals separately for growth, profitability, or balance-sheet claims. Do not declare a universal winner or give buy, sell, or hold instructions.

Use this when the authenticated user asks to review their own ValuEdge portfolio, holdings, market value, fair-value coverage, allocation, concentration, or risk context. Never accepts a user id and never returns another user's data.

Use this when the user wants a bounded ValuEdge stock screen for research candidates such as undervalued, quality, dividend, large-cap, or positive-free-cash-flow stocks. Choose a preset or compose supported filters for undervalued growth and other requests. Use the smallest faithful filter set and state chosen growth/valuation thresholds. Percentages are decimal fractions (0.15 = 15%). Presets only become stricter. The custom baseline requires market cap >=300 million in listing currency and valid canonical fair value. Public screening is NYSE/NASDAQ stocks with a 60-candidate window and at most 12 returned rows, not an exhaustive market scan; disclose incomplete results, source dates, missing coverage and negative-equity caveats. Arbitrary database queries and trade instructions are not supported.

Use this when the user gives an ambiguous company name or ticker and you need to resolve it before valuation or comparison. Search is limited to the ValuEdge-supported security universe.

Use this when the authenticated user asks to review their own ValuEdge Smart Alerts and the valuation context behind them. Never exposes another user's alerts or changes alert state.

Use this when the authenticated user asks to review their own ValuEdge watchlist, including current price, canonical fair value, margin of safety, quality signals, and data freshness. Never accepts a user id.