Skimmer MCP server
README.md
# Skimmer MCP server
Connect Skimmer to ChatGPT, Claude and any AI agent through Cotlet.dev. Skimmer has a public API for Enterprise accounts but no MCP server, checked 16 November 2026. The hosted integration documents 30 tools for schedules, routes, customers, quotes, jobs, work orders, invoices and reports. Quotes, broadcasts and anything that reaches a customer or tech wait for your OK.
## What you can ask
> Move today’s pool stops to another tech and alert them.
> Create a quote for a pool repair and send it only after my approval.
> Show skipped stops and draft alerts for the route team.
> Review aging invoices and set customer invoice dates.
## 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 Skimmer 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 skimmer_agent.py serve
```
Or with Docker:
```bash
docker build -t skimmer-mcp .
docker run -i --rm -e COTLET_API_KEY skimmer-mcp
```
Tools: `skimmer_guide`, `skimmer_status`, `skimmer_open`, `skimmer_read`, `skimmer_click`, `skimmer_type`, `skimmer_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 skimmer_agent.py connect # ready config for ChatGPT, Claude, Claude Code and Cursor
python3 skimmer_agent.py status # is Skimmer ready in your Cotlet.dev account
python3 skimmer_agent.py guide # Skimmer screens and sign-in link
python3 skimmer_agent.py read # open Skimmer, read the page, close the browser
python3 skimmer_agent.py tools # list Cotlet.dev tools
python3 skimmer_agent.py serve # start the stdio MCP server (same as no argument)
```
## Questions from Skimmer users
**Does Skimmer have a public API or official MCP server?**
Skimmer has a public API and webhooks for Enterprise accounts, but no MCP server or official ChatGPT or Claude connector was verified, checked 16 November 2026.
**Where do I sign in to Skimmer?**
Open https://app.getskimmer.com in your Cotlet Cloud Browser and sign in with your own Skimmer account.
**Which actions ask for approval?**
Quotes, broadcasts and anything sent to a customer or tech ask for your OK. Write tools ask first by default; you can switch that off per tool.
**Is Cotlet affiliated with Skimmer?**
No. Cotlet.dev is independent and is not affiliated with Skimmer.
## Learn more
- [Skimmer integration and hosted tools](https://cotlet.dev/integrations/skimmer-api-mcp-server)
---
More: https://cotlet.dev/integrations/skimmer-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=skimmer
Request access: https://cotlet.dev/signup?app=skimmer&utm_source=github&utm_medium=readme&utm_campaign=skimmer
## Workflows on the hosted integration
The live integration page documents these 14 operations:
- `view_schedule`
- `manage_route_assignments`
- `move_scheduled_work`
- `send_tech_alert`
- `manage_customers`
- `import_customers`
- `manage_customer_tags`
- `manage_service_locations`
- `set_service_types`
- `manage_equipment`
- `update_service_rates`
- `manage_quotes`
- `manage_jobs`
- `create_related_invoice`
- `manage_work_orders`
- `manage_recurring_work_orders`
- `manage_work_order_reminders`
- `manage_work_order_types`
- `view_service_history`
- `manage_service_notes`
- `configure_service_checklist`
- `configure_readings_dosages`
- `manage_shopping_list`
- `manage_products`
- `view_reports`
- `set_customer_invoice_dates`
- `configure_invoice_reminders`
- `configure_service_emails`
- `send_broadcast_email`
- `manage_marketing_campaigns`
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.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues