mcpField
G
GlossGenius MCP Server and API by Cotlet

GlossGenius MCP Server and API by Cotlet

Remote
cotlet.devBusiness & Marketing0Updated 2d ago

About GlossGenius MCP Server and API by Cotlet

An MCP server for salon and spa operators using GlossGenius. AI agents can manage appointments and client follow-ups through a signed-in account; it offers a hosted connection and a local stdio option.

Key features

  1. 01Book and reschedule appointments
  2. 02Notify clients about appointment changes
  3. 03Review client visit history
  4. 04Hosted endpoint and local stdio mode

Use cases

  1. 01Book a client for a salon service
  2. 02Move appointments and notify clients
  3. 03Find clients who have not returned

MCP support

Exposes GlossGenius account operations to MCP clients through Cotlet.dev’s hosted server. A local stdio server is also available and forwards tool calls to the hosted service.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://cotlet.dev/mcp/v1/glossgenius/connect
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://cotlet.dev/mcp/v1/glossgenius/connect
Streamable HTTPhttps://cotlet.dev/mcp/v1/glossgeniusAuth required

Tools

Details

From the project README

How to connect GlossGenius to Claude Code, ChatGPT and any AI agent

Yes, Claude, ChatGPT and other AI agents can work in your GlossGenius account. GlossGenius has no official app in the ChatGPT or Claude directories. Cotlet.dev connects your own signed-in GlossGenius account to any AI agent, so you can ask in plain words and the AI books, reschedules and follows up with clients for you.

What you can ask

Book Maria Lopez for a gel manicure on Thursday at 11 am and send her the confirmation.

Who cancelled this week? Offer their open slots to clients who asked for an earlier time.

Move all of my Saturday afternoon appointments to Sunday and let each client know.

Which clients haven't come back in 60 days? List them with their last service and visit date.

Show me tomorrow's schedule and any gaps longer than 45 minutes.

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

{
  "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 GlossGenius 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.

{"mcpServers":{"glossgenius":{"command":"uvx","args":["glossgenius-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

docker build -t glossgenius-mcp .
docker run -i --rm -e COTLET_API_KEY glossgenius-mcp

Tools: glossgenius_guide, glossgenius_status, glossgenius_open, glossgenius_read, glossgenius_click, glossgenius_type, glossgenius_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+, nothing else to install. From PyPI:

pip install glossgenius-mcp        # or run it once: uvx glossgenius-mcp connect
glossgenius-mcp connect

Or straight from this repo:

export COTLET_API_KEY="your-key"
python3 glossgenius_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 glossgenius_agent.py status    # is GlossGenius ready in your Cotlet.dev account
python3 glossgenius_agent.py guide     # GlossGenius screens and sign-in link
python3 glossgenius_agent.py read      # open GlossGenius, read the page, close the browser
python3 glossgenius_agent.py tools     # list Cotlet.dev tools
python3 glossgenius_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from GlossGenius users

Does GlossGenius have an API?

You don't need a GlossGenius API to automate your account. Cotlet.dev works in your own signed-in GlossGenius account directly, so your AI agent can book, reschedule and follow up with clients without an API key.

How do I connect GlossGenius to ChatGPT?

Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to GlossGenius once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no GlossGenius API key.

Is there a way to use Claude with GlossGenius?

Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own GlossGenius account.

Is there a GlossGenius MCP server?

We found no official GlossGenius app in ChatGPT's directory or connector in Claude's directory. Cotlet.dev is a hosted MCP server that works in GlossGenius for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Find it on

Also works with


More: https://cotlet.dev/integrations/glossgenius-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=glossgenius

Start free: https://cotlet.dev/signup?app=glossgenius&utm_source=github&utm_medium=readme&utm_campaign=glossgenius

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.