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

Search the Lab's strategies

Find strategies in the Lab by rule family, series, rebalancing, Sharpe and history length, or those nearly uncorrelated with your own returns (diversifiers for a book). Each row has its id, rule, series and statistics; lab_strategy shows one in full. Remember how many the Lab holds when reading the best of them.

The tool is lab_search 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
familyno
seriesno
rebalanceno
min_sharpeno
min_yearsno
uncorrelated_withno{returns, dates}
max_abs_corrno
sortno
limitno

How a model reaches it

Ask in plain words. The model finds lab_search 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": "lab_search",
  "arguments": {}
}

Words that find it

Besides its name, title and description, find_tool matches a question to lab_search on these words: lab, search, strategies, diversifier, uncorrelated, low, correlation, filter, family, momentum, trend, reversion, volatility.

More

Nothing here is investment advice.