canli-mcp / The desk, built into canli-mcp

A wide price panel from the data lake

Pivot a long dataset (date, symbol, value) into a wide panel, one column per symbol, the latest vintage of each value, or as the lake knew it on as_of, written as CSV in the lake for backtests: prices_file or {"$file": ..., "columns": "all"}. Local server only.

The tool is lake_panel in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It is part of canli-mcp itself, so it is there as soon as canli-mcp is added.

Arguments

As the server declares them
ArgumentRequiredType
datasetyesstring
dateyesstring
symbolyesstring
valueyesstring
symbolsnostring[]
startnodate
endnodate
as_ofnodate
nameyesstring

How a model reaches it

Ask in plain words. The model finds lake_panel with canli-mcp's find_tool, reads its arguments with describe_tool if it needs to, and runs it with run_tool. The call has this shape, with your values in place of the angle brackets:

{
  "name": "lake_panel",
  "arguments": {
    "dataset": "<string>",
    "date": "<string>",
    "symbol": "<string>",
    "value": "<string>",
    "name": "<string>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to lake_panel on these words: panel, pivot, wide, matrix, prices, universe, point, in, time, as, of, backtest, input, multi, asset.

More

Nothing here is investment advice.