research-stocks

Use when the user asks to research a stock, inspect a technical backtest or review saved research for a watchlist. Use get-market-quotes for a simple current quote. Research and simulation results do not establish future returns or place trades.

Connected plugin

Call get_stock_research on the connected WorldMonitor MCP server at https://worldmonitor.app/mcp. Use the user's existing connection; do not ask them to paste an API key into chat. This tool requires a subscription. Explain an access denial and stop; do not retry through a different credential path.

Operation	Arguments	Behavior
`analysis`	`symbols: ["AAPL"]`, optional `include_news`	Current analysis; exactly one ticker. Default no news. Cold generation may use an LLM and save a shared research snapshot.
`backtest`	`symbols: ["AAPL"]`, optional `eval_window_days`	Technical simulation; exactly one ticker. Default 10 trading days, range 3..30. May generate and save a shared result.
`history`	`symbols: ["AAPL", "MSFT"]`, optional `limit_per_symbol`, `include_news`	Read saved analyses. Default four snapshots per ticker, range 1..32. Default no news.
`stored-backtests`	`symbols: ["AAPL", "MSFT"]`, optional `eval_window_days`	Read saved backtests without generating new ones. Default ten trading days.

Stored-result operations accept up to 50 symbols. Use only options supported by the chosen operation. Never silently drop requested tickers; narrow the batch or use jmespath if the output budget is exceeded.

The response is {operation, data}. Read available before numerical results. Retain generated/analysis timestamps, provider, model, fallback, engineVersion, risk factors and any ratingBasis. Empty saved results mean no stored research returned, not a zero return. Technical backtests omit point-in-time fundamentals and are simulations, not actual trading results. Distinguish technical signals from fundamentals-blended ratings. Do not present source-generated actions as a personalized recommendation.