How to connect Mangomint to Claude Code, ChatGPT and any AI agent
Yes, Claude, ChatGPT and other AI agents can work in your Mangomint account. Mangomint has no public API and no official MCP server, only outbound webhooks. Cotlet.dev connects your own signed-in Mangomint account to any AI agent, so you can ask in plain words and the AI books, checks and replies for you.
What you can ask
Book Anna Kowalski for a balayage with Sam on Friday at 2 pm and text her the confirmation.
What does tomorrow look like per stylist? List gaps longer than an hour.
Reply to the unread client messages in the inbox. Show me the drafts first.
Which clients haven't booked in 90 days? Make a list with their last service.
Move all of Jess's Saturday appointments to Kim and tell the clients.
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}"
}
}
}
}
Command line
Python 3.10+, nothing else to install. From PyPI:
pip install mangomint-mcp # or run it once: uvx mangomint-mcp connect
mangomint-mcp connect
Or straight from this repo:
export COTLET_API_KEY="your-key"
python3 mangomint_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 mangomint_agent.py status # is Mangomint ready in your Cotlet.dev account
python3 mangomint_agent.py guide # Mangomint screens and sign-in link
python3 mangomint_agent.py read # open Mangomint, read the page, close the browser
python3 mangomint_agent.py tools # list Cotlet.dev tools
Questions from Mangomint users
Does Mangomint have an API?
Mangomint has no public, self-service API. It offers outbound webhooks that send events to other apps, but they can't read or change your bookings. Cotlet.dev works in your Mangomint account directly, so your AI agent can do both.
How do I connect Mangomint to ChatGPT?
Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to Mangomint once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Mangomint API key.
Is there a way to use Claude with Mangomint?
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 Mangomint account.
Is there a Mangomint MCP server?
Mangomint has no official MCP server. Cotlet.dev is a hosted MCP server that works in Mangomint for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.
Also works with
Start free: https://cotlet.dev/signup?app=mangomint&utm_source=github&utm_medium=readme&utm_campaign=mangomint
Metadata
Release files for mangomint-mcp 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mangomint_mcp-1.0.0.tar.gz | 6.1 kB | With provenance | Details for mangomint_mcp-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mangomint_mcp-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for mangomint_mcp-1.0.0-py3-none-any.whl |
Total release size: 12.6 kB
Release files / mangomint_mcp-1.0.0.tar.gz
| Download URL | mangomint_mcp-1.0.0.tar.gz |
|---|---|
| Size | 6.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
16a975c27dbe9f3242c801080c942b04e4bbccc7266f51664268df55de17e1c2
|
|
BLAKE2b-256 checksum How to use checksums |
62bfea0841bd72aa94ca600466effa83d898a8a94928924c5b13c317b66b7f2c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.
Transparency logRelease files / mangomint_mcp-1.0.0-py3-none-any.whl
| Download URL | mangomint_mcp-1.0.0-py3-none-any.whl |
|---|---|
| Size | 6.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
69df59c9ec4b4e55b8c399c7e742b82e7ae0043c2480422d668633b3a2741cad
|
|
BLAKE2b-256 checksum How to use checksums |
d513c3647f867f9b067394673f9be61cd34cb2d44d18654b86cf7c812bbcf978
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.
Transparency logSecurity for mangomint-mcp 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for mangomint_mcp-1.0.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.