canli-mcp / Compare stocks

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.

Add to CursorAdd to VS Code

Free and MIT-licensed. No account and no API key. Or run claude mcp add canli -- npx -y canli-mcp in Claude Code.

Ask it

Compare SPY, AAPL, NVDA, GLD and TLT over five years.

The agent finds the tool through canli-mcp's find_tool and runs it through run_tool. This is the call:

{
  "calls": [
    {
      "name": "price_history",
      "arguments": {
        "symbol": "SPY",
        "start": "2024-01-01",
        "interval": "1Week"
      }
    },
    {
      "name": "price_history",
      "arguments": {
        "symbol": "GLD",
        "start": "2024-01-01",
        "interval": "1Week"
      }
    }
  ],
  "return": "all"
}

What came back

Recorded from canli-mcp 0.11.1 on 2026-10-25, with no API key set. The model read 17,676 characters.

What price_history, call 1 returned, the latest rows
dateclose
2026-09-07762.397
2026-09-14761.69
2026-09-21771.35
2026-09-28769.64
2026-10-05778.57
2026-10-12763.25
2026-10-19759.97
2026-10-23759.97
The result price_history, call 1 sent back, in full form
{
  "symbol": "SPY",
  "interval": "1Week",
  "adjusted": true,
  "start": "2024-01-01",
  "end": "2026-10-23",
  "count": 148,
  "change": {
    "from": "2024-01-01",
    "to": "2026-10-23",
    "total_return": 0.677295
  },
  "dates": [
    "2024-01-01",
    "2024-01-08",
    "2024-01-15",
    "2024-01-22",
    "2024-01-29",
    "2024-02-05",
    "…"
  ],
  "open": [
    457.198,
    453.586,
    460.2,
    468.673,
    472.275,
    478.056,
    "…"
  ],
  "high": [
    458.66,
    463.434,
    467.424,
    473.621,
    480.331,
    485.754,
    "…"
  ],
  "low": [
    451.65,
    453.461,
    454.981,
    467.482,
    467.559,
    474.696,
    "…"
  ],
  "close": [
    453.093,
    461.575,
    467.143,
    471.965,
    478.685,
    485.318,
    "…"
  ],
  "volume": [
    397560700,
    344088200,
    356549500,
    356721800,
    437072100,
    318555200,
    "…"
  ],
  "currency": "USD",
  "exchange": "NYSEArca",
  "asset_class": "etf",
  "name": "State Street SPDR S&P 500 ETF Trust",
  "dividends": [
    [
      "2024-03-15",
      1.595
    ],
    [
      "2024-06-21",
      1.759
    ],
    [
      "2024-09-20",
      1.746
    ],
    [
      "2024-12-20",
      1.966
    ],
    [
      "2025-03-21",
      1.696
    ],
    [
      "2025-06-20",
      1.761
    ],
    "…"
  ],
  "splits": [],
  "source": "Yahoo Finance chart data (no key)",
  "limits": [
    "Yahoo Finance's public chart data: unofficial, for personal use under Yahoo's terms, and it can change or stop without notice. Set ALPACA_AP…",
    "Not investment advice."
  ]
}
What price_history, call 2 returned, the latest rows
dateclose
2026-09-07398.77
2026-09-14401.17
2026-09-21393.41
2026-09-28380.14
2026-10-05384.58
2026-10-12382.01
2026-10-19366.61
2026-10-23366.61
The result price_history, call 2 sent back, in full form
{
  "symbol": "GLD",
  "interval": "1Week",
  "adjusted": true,
  "start": "2024-01-01",
  "end": "2026-10-23",
  "count": 148,
  "change": {
    "from": "2024-01-01",
    "to": "2026-10-23",
    "total_return": 0.93615
  },
  "dates": [
    "2024-01-01",
    "2024-01-08",
    "2024-01-15",
    "2024-01-22",
    "2024-01-29",
    "2024-02-05",
    "…"
  ],
  "open": [
    191.44,
    187.21,
    189.15,
    187.23,
    188.31,
    186.88,
    "…"
  ],
  "high": [
    191.89,
    191.08,
    189.26,
    188.37,
    191.36,
    189.39,
    "…"
  ],
  "low": [
    188.16,
    186.56,
    185.45,
    186.32,
    187.19,
    186.7,
    "…"
  ],
  "close": [
    189.35,
    189.71,
    187.93,
    187.01,
    188.61,
    187.6,
    "…"
  ],
  "volume": [
    26585800,
    28821800,
    25596200,
    25239500,
    36108000,
    24865000,
    "…"
  ],
  "currency": "USD",
  "exchange": "NYSEArca",
  "asset_class": "etf",
  "name": "SPDR Gold Shares",
  "dividends": [],
  "splits": [],
  "source": "Yahoo Finance chart data (no key)",
  "limits": [
    "Yahoo Finance's public chart data: unofficial, for personal use under Yahoo's terms, and it can change or stop without notice. Set ALPACA_AP…",
    "Not investment advice."
  ]
}

Prices, filings and statistics are as the sources published them on that day; run the call again for today's. Nothing here is investment advice.

The same answer as a view

In a host that draws MCP Apps, view: true shows the person the whole result and gives the model a summary. Watch it, then try it: below the clip is canli-mcp's real view, playing a recording.

Compare stocks

The view loads here.

The tools behind the answer

From canli-mcp's tool index
ToolPackWhat it does
price_historymarketsPrice bars (open, high, low, close, volume), daily to hourly, for US stocks and ETFs, stocks listed abroad (SAP.DE, 7203.T), currency pairs (EUR/USD), futures (crude oil, gold), indices and yields (S&P 500, VIX, 10 year yield) and crypto (bitcoin), by symbol or plain name. Stocks adjust for splits and dividends by default, with dividends, splits and the total return; returns: true adds daily returns. No key needed; uses the user's Alpaca or Tiingo key for US stocks when set.

Add canli-mcp

Claude Code
claude mcp add canli -- npx -y canli-mcp
Cursor, Claude Desktop or any MCP client
{ "mcpServers": { "canli": { "command": "npx", "args": ["-y", "canli-mcp"] } } }
claude.ai, ChatGPT or any client that takes a URL
https://canlicapital.com/mcp/canli

Everything canli-mcp does · How it compares with other finance MCP servers

Related questions