SlickPic MCP server
# SlickPic MCP server for ChatGPT and Claude
**Connect SlickPic to ChatGPT, Claude and other AI agents through Cotlet.dev.** Work in your own signed-in Cloud Browser to review client picks, organize albums, set gallery privacy and prepare photo delivery. Client-facing actions wait for your confirmation.
## What you can ask
> Read each client's picks and comments on my proofing album.
> Prepare a password-protected proofing link for my approval.
> Set the final gallery download options.
> Review album privacy as a visitor.
> Prepare a group upload album for guest photos.
## Connect your agent
Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.
### ChatGPT
Settings > Apps & Connectors > Create. Add `https://cotlet.dev/mcp/v1/connect` and use OAuth to sign in to Cotlet.dev.
### Claude
Settings > Connectors > Add custom connector. Add `https://cotlet.dev/mcp/v1/connect` and sign in to 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 SlickPic 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 source directly:
```bash
export COTLET_API_KEY="your-key"
python3 slickpic_agent.py serve
```
Or with Docker:
```bash
docker build -t slickpic-mcp .
docker run -i --rm -e COTLET_API_KEY slickpic-mcp
```
Tools: `slickpic_guide`, `slickpic_status`, `slickpic_open`, `slickpic_read`, `slickpic_click`, `slickpic_type`, `slickpic_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 this repository:
```bash
export COTLET_API_KEY="your-key"
python3 slickpic_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 slickpic_agent.py status # is SlickPic ready in your Cotlet.dev account
python3 slickpic_agent.py guide # SlickPic screens and sign-in link
python3 slickpic_agent.py read # open SlickPic, read the page, close the browser
python3 slickpic_agent.py tools # list Cotlet.dev tools
python3 slickpic_agent.py serve # start the stdio MCP server (same as no argument)
```
## Questions from SlickPic users
**Does SlickPic have an API or MCP server?**
The Cotlet.dev page, checked 16 November 2026, found no public SlickPic API documentation, SlickPic MCP server or official ChatGPT or Claude connector. SlickPic offers upload plug-ins for photography applications. Cotlet.dev provides an independent hosted connection.
**How do I connect SlickPic to ChatGPT?**
Sign up at https://cotlet.dev/signup?app=slickpic and sign in to SlickPic in your Cotlet.dev Cloud Browser. In ChatGPT, add https://cotlet.dev/mcp/v1/connect with OAuth.
**Can I connect SlickPic to Claude?**
Yes. Add https://cotlet.dev/mcp/v1/connect as a custom connector in Claude, then sign in to Cotlet.dev.
**Is this an official SlickPic integration?**
No. Cotlet.dev is independent and is not affiliated with, endorsed by or sponsored by SlickPic.
---
More: https://cotlet.dev/integrations/slickpic-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=slickpic
Start free: https://cotlet.dev/signup?app=slickpic&utm_source=github&utm_medium=readme&utm_campaign=slickpic
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: guide/status are informational/setup, while open/read/click/type/close form an unambiguous browser interaction loop. There is little risk of an agent confusing one tool for another.
All seven tools use lowercase snake_case with the same slickpic_ prefix and short, predictable labels. The only slight variation is guide/status as state/info labels, but the naming remains consistent overall.
Seven tools is a well-scoped set for browser-based SlickPic automation: setup, session open/close, page reading, and clicking/typing. Each tool earns its place without obvious redundancy.
The core lifecycle is covered: onboarding/status, opening a page, reading it, interacting via click/type, and closing the session. Minor gaps exist for advanced browser actions such as explicit navigation, waiting, or file upload, but the main workflow is supported.