Finance questions canli-mcp answers

• How do I get stock prices in Claude?

  Add canli-mcp to Claude and ask for the prices. It reads daily, weekly or monthly bars for US stocks, ETFs and indexes with no API key, and draws them as a candlestick chart with moving averages, RSI and MACD in hosts that show MCP Apps.

• How can an AI agent read a company's financial statements from SEC filings?

  canli-mcp's financial_statements tool reads the income statement, balance sheet and cash flow straight from the XBRL a company filed with the SEC. Several years come joined in one table, and a restated figure is shown beside the one first reported, so the agent quotes the filing rather than its memory.

• How do I backtest a trading strategy in Claude?

  Ask Claude to backtest it with canli-mcp. The backtest runs on your machine over real prices, reports return, Sharpe and drawdown, and counts every setting you tried, so it can tell you how much of the result luck would explain. In hosts that draw MCP Apps the sliders rerun it in place.

• Is there an MCP server for options chains?

  Yes. canli-mcp's options_chain tool returns calls and puts for a US stock or ETF with bid, ask, volume, open interest and implied volatility, for any listed expiration, with no API key. volatility_surface puts the whole chain on one surface.

• How do I get an implied volatility surface into an AI chat?

  Ask for it through canli-mcp. volatility_surface reads every listed expiration of a US option chain and returns the smile at each one and the at-the-money term structure, drawn as a heatmap and curves in hosts that show MCP Apps.

• How can an AI agent get the Treasury yield curve?

  canli-mcp's treasury_yields tool reads the daily par yield curve from the US Treasury itself: nominal, real or bills, for any date or range. In hosts that draw MCP Apps the curve is drawn against earlier dates and can be played through time.

• How do I compare several stocks' returns and correlation in Claude?

  Use canli-mcp's compare_stocks prompt, or ask for the prices of each ticker. You get growth of one dollar, return and risk statistics side by side, a correlation heatmap and the number of independent bets the set adds up to.

• How do I get today's market overview in an AI chat?

  Ask for it with canli-mcp's market_overview tool. It returns the main US and world indexes, rates, commodities, currencies and crypto with the day's moves, as a market map whose tiles open their charts in hosts that draw MCP Apps.

• How do I see insider trading (Form 4 filings) with an AI agent?

  canli-mcp's insider_trades tool reads a company's Form 4 filings from SEC EDGAR: who traded, buy or sell, shares, price and what they hold after, each linked to its filing. planned_insider_sales adds the sales announced ahead on Form 144.

• How can an AI agent read a hedge fund's 13F holdings?

  Ask canli-mcp's fund_holdings tool for the manager. It reads the 13F filings on SEC EDGAR, lists the top positions with value and share counts, and can compare a quarter with the one before to show what was bought and sold.

• How do I fact-check the financial figures an AI wrote?

  Give the draft to canli-mcp's verify_claims tool with the company. It finds each figure in the text and checks it against the filings: confirmed, contradicted (with the filed figure and what the wrong number matches) or not reported.

• How do I tell whether a backtest is overfit?

  Count how many settings were tried and correct the Sharpe ratio for it. canli-mcp's validate_deflated_sharpe gives the probability that the true Sharpe is above zero after that many trials, and validate_overfitting, validate_reality_check and placebo_test go further, all on your machine.

• How can an AI agent get economic data like inflation and unemployment?

  canli-mcp's economic_series tool reads official statistics such as CPI, unemployment and GDP at the source, with year-on-year and other changes computed for you. economic_calendar lists the releases coming up and world_economy covers other countries.

• How can an AI agent look up Federal Reserve rate decisions?

  canli-mcp's fomc tool lists the FOMC meetings for a year with the target range decided at each one and the projections published with them, read from the Federal Reserve.

• How do I get an earnings calendar in an AI chat?

  Ask canli-mcp's earnings_calendar tool, for one company or the market. earnings_release then reads the release itself, with guidance as ranges and last quarter's guidance set against the results.

• How can an AI agent check a stock's short interest?

  canli-mcp's short_interest tool reads the short positions exchanges report twice a month, with days to cover and the change from the last report, for one stock or ranked across the market.

• How do I get point-in-time fundamentals without lookahead bias?

  Ask canli-mcp what was known on a date. known_as_of returns a company's figures as they had been filed by then, so a backtest never uses a number the market had not seen, and restatements shows every later change.

• Can an AI agent screen stocks by fundamentals?

  Yes. canli-mcp's screen_companies tool screens every US-listed company on figures from their filings, such as revenue growth, margins or valuation, and sorts the result.

• How can an AI agent see what an ETF or mutual fund holds?

  canli-mcp's fund_portfolio tool reads a fund's N-PORT filings on SEC EDGAR and lists its top holdings with weights, and can compare a period with the one before.

• How do I price an option with Black-Scholes in Claude?

  canli-mcp's black_scholes tool prices a European call or put and returns its greeks, computed exactly on your machine rather than estimated by the model. implied_volatility, american_option and option_strategy_payoff cover the rest.

• How can an AI agent compute technical indicators like RSI and MACD?

  canli-mcp computes them exactly on your machine: rsi, macd, bollinger_bands and dozens more, from prices it reads itself or you pass in, so the model never estimates an indicator in its head.

• How can an AI agent search SEC filings?

  canli-mcp's search_filings tool runs a full-text search over SEC EDGAR filings by phrase, form, company and date, and read_filing opens any result by section, so the agent quotes the filing it found.

• How can an AI agent tell what growth a stock price implies?

  canli-mcp's company_reverse_dcf works back from today's price to the cash-flow growth it implies, using the company's own filed cash flows, with the discount rate and terminal growth you choose.

Everything canli-mcp does