Action Shift
Free for restaurant owners. Drop last night's close, get the one thing to fix before next shift.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"action-shift-mcp": {
"url": "https://action-shift-mcp.vercel.app/mcp"
}
}
}Remote endpoints
https://action-shift-mcp.vercel.app/mcpstreamable-httpWhat it can do
Tool inventory
Tools (1)
🟢action_shift_read_close(store, salesBasis, businessDate, grossSales, orderCount, ...)
Read a restaurant close and return the Owner desk line, one Do this first finding, Not verified here, a 3-step next move, and at most 2 If time items, to fix before the next shift from numbers in a restaurant close (POS export, Z report, pasted text). Pass only numbers that appear in the close. Deterministic; no data stored.
Input Schema
{
"type": "object",
"properties": {
"store": {
"type": "string"
},
"salesBasis": {
"type": "string",
"description": "net, gross, or Subtotal, as labeled on the close"
},
"businessDate": {
"type": "string"
},
"grossSales": {
"type": "number",
"description": "Sales for the shift/day from the close (required, > 0)"
},
"orderCount": {
"type": "number"
},
"laborDollars": {
"type": "number"
},
"laborTargetPct": {
"type": "number",
"description": "Operator's own labor % target. Never assume one."
},
"expectedCash": {
"type": "number"
},
"enteredDeposit": {
"type": "number"
},
"payouts": {
"type": "number"
},
"discounts": {
"type": "number"
},
"promotions": {
"type": "number"
},
"voids": {
"type": "number"
},
"lateDeliveryCount": {
"type": "number"
},
"lateDeliverySales": {
"type": "number"
},
"averageDeliveryMinutes": {
"type": "number"
},
"targetDeliveryMinutes": {
"type": "number"
}
},
"required": [
"grossSales"
]
}Community
Evidence