Glamorph MCP server
README.md
# Glamorph MCP server
Connect Glamorph to ChatGPT, Claude and any AI agent through Cotlet.dev. Work in your own Glamorph account with 18 hosted tools for appointments, clients, forms, photos and money records. The six read tools run immediately; all twelve write tools ask for approval by default.
## What you can ask
> Show tomorrow's appointments and brief me on each client.
> Prepare an intake and consent pack for a new client, then ask me before sending it.
> Show the recorded income and expenses for this month.
## 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 Glamorph 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 glamorph_agent.py serve
```
Or with Docker:
```bash
docker build -t glamorph-mcp .
docker run -i --rm -e COTLET_API_KEY glamorph-mcp
```
Tools: `glamorph_guide`, `glamorph_status`, `glamorph_open`, `glamorph_read`, `glamorph_click`, `glamorph_type`, `glamorph_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 glamorph_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 glamorph_agent.py status # is Glamorph ready in your Cotlet.dev account
python3 glamorph_agent.py guide # Glamorph screens and sign-in link
python3 glamorph_agent.py read # open Glamorph, read the page, close the browser
python3 glamorph_agent.py tools # list Cotlet.dev tools
python3 glamorph_agent.py serve # start the stdio MCP server (same as no argument)
```
## Questions from Glamorph users
**How do I sign in to Glamorph?**
Open https://app.glamorph.com/login in your Cotlet Cloud Browser and complete Continue with Apple or Continue with Google yourself.
**Which actions ask for approval?**
All twelve write tools ask for approval by default, including bookings, forms, shared galleries and payments. The six read tools run immediately.
**Is Cotlet affiliated with Glamorph?**
No. Cotlet.dev is independent and not affiliated with Glamorph.
## Learn more
- [Glamorph integration and hosted tools](https://cotlet.dev/integrations/glamorph-api-mcp-server)
---
More: https://cotlet.dev/integrations/glamorph-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=glamorph
Request access: https://cotlet.dev/signup?app=glamorph&utm_source=github&utm_medium=readme&utm_campaign=glamorph
## Workflows on the hosted integration
The live integration page documents these 18 operations:
- `get_calendar`
- `create_appointment`
- `update_appointment`
- `respond_booking_request`
- `list_reminder_history`
- `search_clients`
- `get_client_history`
- `update_client_record`
- `tag_client_photos`
- `share_album`
- `send_document`
- `collect_payment`
- `list_client_packages`
- `manage_packages`
- `record_expense`
- `get_money_summary`
- `set_booking_page`
- `set_team_schedule`
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