Restroworks Restaurant POS MCP server
# Restroworks Restaurant POS MCP server
Connect Restroworks Restaurant POS to ChatGPT, Claude and any AI agent through Cotlet.dev. Review sales across outlets, inspect flagged bills, read inventory and manage menus in your own signed-in account. Write actions ask for approval by default.
## What you can ask
> Rank yesterday's sales by outlet.
> Show the open orders and kitchen queue for Downtown.
> Review tomorrow's suggested order before approving it.
## Connect in 2 minutes
Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.
### ChatGPT
Settings → Apps & Connectors → Create, with connector URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev. No API key needed.
### Claude
Settings → Connectors → Add custom connector, with URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev.
### Claude Code
```bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
```
### Cursor
Copy `.cursor/mcp.json` from this repo into your project:
```json
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}
```
## Run it locally (stdio)
This repo is a real MCP server. It speaks MCP over stdio, lists its Restroworks Restaurant POS tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.
Run the included Python module with Python 3.10 or later:
```bash
python3 restroworks_restaurant_pos_agent.py serve
```
Or with Docker:
```bash
docker build -t restroworks-restaurant-pos-mcp .
docker run -i --rm -e COTLET_API_KEY restroworks-restaurant-pos-mcp
```
Tools: `restroworks_restaurant_pos_guide`, `restroworks_restaurant_pos_status`, `restroworks_restaurant_pos_open`, `restroworks_restaurant_pos_read`, `restroworks_restaurant_pos_click`, `restroworks_restaurant_pos_type`, `restroworks_restaurant_pos_close`. Without `COTLET_API_KEY` a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
## Command line
Python 3.10+, with no third-party runtime dependencies. Clone this repository and run:
```bash
export COTLET_API_KEY="your-key"
python3 restroworks_restaurant_pos_agent.py connect # ready config for ChatGPT, Claude, Claude Code and Cursor
python3 restroworks_restaurant_pos_agent.py status # is Restroworks Restaurant POS ready in your Cotlet.dev account
python3 restroworks_restaurant_pos_agent.py guide # Restroworks Restaurant POS screens and sign-in link
python3 restroworks_restaurant_pos_agent.py read # open Restroworks Restaurant POS, read the page, close the browser
python3 restroworks_restaurant_pos_agent.py tools # list Cotlet.dev tools
python3 restroworks_restaurant_pos_agent.py serve # start the stdio MCP server (same as no argument)
```
## Questions from Restroworks Restaurant POS users
**Where do I sign in?**
Use your restaurant's own Restroworks address, in the form `<your-restaurant>.restroworks.biz/login`, in your Cotlet Cloud Browser.
**Which user should I use?**
Use an area manager login for its region or a brand head login for their brands. The tools see the outlets your role covers.
**Can the agent take payments or settle bills?**
No. The order and table tools only read. No tool takes payment or settles a bill.
**Is Cotlet affiliated with Restroworks?**
No. Cotlet.dev is independent and not affiliated with Restroworks.
## Learn more
- [Restroworks Restaurant POS integration and hosted tools](https://cotlet.dev/integrations/restroworks-restaurant-pos-api-mcp-server)
---
More: https://cotlet.dev/integrations/restroworks-restaurant-pos-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=restroworks-restaurant-pos
Request access: https://cotlet.dev/signup?app=restroworks-restaurant-pos&utm_source=github&utm_medium=readme&utm_campaign=restroworks-restaurant-pos
## Workflows on the hosted integration
The live integration page documents these 18 operations:
- `get_sales_report`
- `get_outlet_dashboard`
- `review_theft_flags`
- `list_orders`
- `get_table_status`
- `update_floor_layout`
- `manage_reservations`
- `manage_waitlist`
- `get_kitchen_queue`
- `get_production_forecast`
- `plan_central_kitchen`
- `get_inventory_levels`
- `update_recipe`
- `review_suggested_order`
- `create_purchase_order`
- `update_menu`
- `set_item_availability`
- `update_menu_boards`
The local stdio adapter exposes seven browser helpers listed above. These helpers forward to Cotlet.dev; the workflow operations are documented on the hosted integration page.
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: guidance, readiness check, browser session open/close, page reading, clicking, and typing. The boundary between guide and status is explained well enough, and no two tools overlap in operation.
All tools follow the same restroworks_restaurant_pos_<action> pattern with a consistent shared prefix. The action suffixes are simple and predictable.
Seven tools is a well-scoped set for a browser-driven POS automation server. Each tool maps to an essential workflow primitive, with no obvious padding.
The set covers the core browser automation lifecycle: orient, check readiness, open, read, click, type, and close. Minor gaps exist around explicit navigation/back/refresh, waiting for page load, or keyboard actions, but agents can likely work around them.