picdrop MCP server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@picdrop MCP server Compare this image with its previous edit in picdrop"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
picdrop MCP server
Connect picdrop to ChatGPT, Claude and other AI agents through Cotlet.dev. Review saved sets and color flags, compare image versions and prepare a retouching handoff in your signed-in picdrop account.
What you can ask
Review the client's saved set and color flags in the gallery I select.
Compare this image with its previous edit.
Export selected filenames and summarize requested changes for the retoucher.
Related MCP server: SmugMCP
Connect in 2 minutes
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
ChatGPT
Settings → Apps → add connector URL https://cotlet.dev/mcp/v1/connect, then sign in with Cotlet.dev. No API key needed.
Claude Code
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:
{
"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 picdrop 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:
python3 picdrop_agent.py serveOr with Docker:
docker build -t picdrop-mcp .
docker run -i --rm -e COTLET_API_KEY picdrop-mcpTools: picdrop_guide, picdrop_status, picdrop_open, picdrop_read, picdrop_click, picdrop_type, picdrop_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:
export COTLET_API_KEY="your-key"
python3 picdrop_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 picdrop_agent.py status # is picdrop ready in your Cotlet.dev account
python3 picdrop_agent.py guide # picdrop screens and sign-in link
python3 picdrop_agent.py read # open picdrop, read the page, close the browser
python3 picdrop_agent.py tools # list Cotlet.dev tools
python3 picdrop_agent.py serve # start the stdio MCP server (same as no argument)Questions from picdrop users
How do I connect my account?
Request access at https://cotlet.dev/signup?app=picdrop, sign in to picdrop in your Cotlet.dev Cloud Browser and enable it for agents.
Can I compare image versions?
Yes. File Versions must be enabled on a supported picdrop plan.
Is there an official picdrop connection?
picdrop documents an official MCP connection. See the live integration page for its documented scope and comparison.
Is Cotlet.dev affiliated with picdrop?
No. Cotlet.dev is independent and not affiliated with picdrop.
Learn more
Request access: https://cotlet.dev/signup?app=picdrop&utm_source=github&utm_medium=readme&utm_campaign=picdrop
Workflows on the hosted integration
Examples documented on the live integration page:
dashboard_browsedashboard_sortfile_downloadcontact_sheetgallery_client_previewfile_viewfile_versions_comparegallery_filter
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.
Available Tools
7 toolspicdrop_clickB
Click a numbered element on the current picdrop page.
Inputs: element (required).
picdrop_closeA
Close the picdrop browser session when the work is done, so credits stop running.
Inputs: no named parameters.
picdrop_guideA
How to work in picdrop (review client selections and compare image versions): its screens and the sign-in link. Call this first.
Inputs: task.
picdrop_openB
Open a picdrop page in your signed-in Cloud Browser (default https://www.picdrop.com) to work with review client selections and compare image versions.
Inputs: url.
picdrop_readA
Read the current picdrop page: its text and numbered buttons, links and fields.
Inputs: element.
picdrop_statusA
Check that your Cotlet.dev account and picdrop are ready: account, credits and picdrop connection.
Inputs: no named parameters.
picdrop_typeB
Type text into a numbered field on the current picdrop page.
Inputs: text (required), element (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
The tools split cleanly into setup (guide, status, open) and page interaction (read, click, type, close), with descriptions that clarify when to use each. The three setup tools share the same domain phrasing ('review client selections and compare image versions'), so an agent must read the descriptions to distinguish guidance, account checks, and actual page opening.
Every tool uses the same picdrop_<action> pattern with short, unambiguous verbs (open, read, click, type, close, guide, status). The convention is predictable throughout and maps directly onto a browser-session lifecycle.
Seven tools is well within the ideal range for a browser-automation wrapper and each one earns its place in the open → read → act → close flow. Nothing feels redundant or missing from a count perspective.
The core interaction loop (open, read, click, type, close) plus guide/status covers basic navigation, but common browser needs are absent: no scroll, back/goto navigation, keyboard submit, screenshot, or file upload/download. For a picdrop workflow involving comparing image versions and reviewing client selections, the lack of any visual/image-capture capability is a notable gap.
Maintenance
Related MCP Connectors
Ask an AI about your photo galleries and client picks, or create a new gallery.
Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools.
OAuth account tools, image/video generation (Pro), Studio handoffs. No local vault access.
Search photos and video moments by visual meaning, people, dates, and folders across local libraries, Apple Photos, and OneDrive. Manage collections, groups, favorites, people, and duplicate review. Synced metadata remains searchable while the desktop is offline; local and Apple Photos media access needs the owning device online with remote access enabled. OneDrive media can be accessed directly from the cloud. OAuth or Bearer API keys. Paid Cloud Access required; hosted visual search uses prepaid credits. Text-in-image search is semantic matching, not guaranteed exact OCR. Setup: https://organizewith.ai/en/guides/connect-ai-assistants
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables ChatGPT users to search and browse a private photo library, inspect metadata, and receive real image previews through read-only tools, while keeping encrypted sessions server-side.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to manage a user's own SmugMug account in plain language — creating and securing galleries, auditing visits, renaming and organizing photos, and applying price lists — without needing a SmugMug API key, OAuth setup, or code.795 PyPIElastic 2.0
- AlicenseNot gradedqualityCmaintenanceEnables users to generate, edit, and iteratively refine images through a logged-in ChatGPT web session, while managing image libraries, style presets, character profiles, and background jobs.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to work in a user's signed-in photo library account to find, tag, organize, and share photos through natural-language requests, without requiring a separate API key.7Elastic 2.0