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

Name: Pixieset MCP Server and API by Cotlet
Author: cotlet

Yes, Claude, ChatGPT and other AI agents can work in your Pixieset account. As of November 2026, Pixieset has no official app in ChatGPT and no official connector in Claude. Cotlet.dev connects your own signed-in Pixieset account to any AI agent, so you can ask in plain words and the AI delivers galleries, books sessions and follows up with clients for you.

What you can ask

Send the Martinez wedding gallery to Elena and set it to expire in 30 days.

Which sessions are booked next week? List the client, date, time and package.

Book Jordan Lee for a 1-hour family session on Saturday at 10 am and send the contract and invoice.

Which galleries delivered in the last 14 days haven't been viewed yet? Draft a friendly reminder for each client.

List unpaid invoices over $500 and email those clients a payment reminder.

Connect in 2 minutes

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

Claude Code

bash

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:

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 Pixieset 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.

json

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

Or with Docker:

bash

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

Tools: pixieset_guide, pixieset_status, pixieset_open, pixieset_read, pixieset_click, pixieset_type, pixieset_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:

bash

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

Or straight from this repo:

bash

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

Questions from Pixieset users

Does Pixieset have an API?

You don't need one. Cotlet.dev works in your own signed-in Pixieset account, so your AI agent can deliver galleries, manage bookings and follow up with clients without a Pixieset API key.

How do I connect Pixieset to ChatGPT?

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

Is there a way to use Claude with Pixieset?

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 Pixieset account.

Is there a Pixieset MCP server?

Pixieset's Apps & Plugins page lists no ChatGPT or Claude integration. Cotlet.dev is a hosted MCP server that works in Pixieset for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.