canli-mcp / Quant finance

Beneish M-score

Compute the eight-variable Beneish M-score earnings-manipulation screen from two years of statements, with every index; above -1.78 flags likely manipulation.

The tool is beneish_m_score in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It comes from canli-quant-mcp, which canli-mcp includes, and it is also its own server.

Arguments

As the server declares them
ArgumentRequiredType
currentyes{receivables,revenue,cost_of_goods_sold,current_assets,ppe,securities,total_assets,depreciation,sga,current_liabilities,long_term_debt,net_income,operating_cash_flow}
prioryes{receivables,revenue,cost_of_goods_sold,current_assets,ppe,securities,total_assets,depreciation,sga,current_liabilities,long_term_debt,net_income,operating_cash_flow}

How a model reaches it

Ask in plain words. The model finds beneish_m_score 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": "beneish_m_score",
  "arguments": {
    "current": "<{receivables,revenue,cost_of_goods_sold,current_assets,ppe,securities,total_assets,depreciation,sga,current_liabilities,long_term_debt,net_income,operating_cash_flow}>",
    "prior": "<{receivables,revenue,cost_of_goods_sold,current_assets,ppe,securities,total_assets,depreciation,sga,current_liabilities,long_term_debt,net_income,operating_cash_flow}>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to beneish_m_score on these words: beneish, m, score, earnings, manipulation, accounting, fraud, accruals, forensic.

More

Nothing here is investment advice.