CloudSpot MCP server through Cotlet.dev
Connect CloudSpot to ChatGPT, Claude, Codex and Claude Code through Cotlet.dev. Manage galleries, clients, projects and documents in your own signed-in CloudSpot account.
This is an unofficial integration, not affiliated with CloudSpot. Cotlet.dev hosts the connection through your Cloud Browser. This repository provides an optional Python stdio MCP bridge.
Connect your account
- Request access to CloudSpot.
- Open https://app.cloudspot.io/login in your Cotlet.dev Cloud Browser, sign in yourself and enable CloudSpot for agents.
- Connect your agent. Refresh the connector if you enabled CloudSpot after connecting.
ChatGPT
Open Settings > Apps & Connectors > Create. Enter https://cotlet.dev/mcp/v1/connect as the MCP server URL and choose OAuth.
Claude
Open Settings > Connectors > Add custom connector and enter https://cotlet.dev/mcp/v1/connect.
Codex
Create a Cotlet.dev API key in your console and set COTLET_API_KEY in your environment. Add:
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
Claude Code
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
Photography studio workflows
Examples based on the live CloudSpot integration reference:
- Read galleries and see the favorites and downloads in Collection Analytics.
- Create a Collection and deliver a Gallery with an optional Zip download.
- Turn an inquiry into a Project and prepare contracts and questionnaires.
- Draft an invoice and payment schedule, then approve sending it.
- Set up mini-sessions and reschedule bookings.
- Review pending print orders before sending them to the lab.
The live reference lists 17 capabilities: 2 read and 15 write. The hosted groups are cloudspot_read and cloudspot_write.
read_galleriesview_collection_analyticscreate_collectiondeliver_imagesset_gallery_expirationmanage_leadsmanage_clientsmanage_projectsmanage_to_dosmanage_contractsmanage_questionnairesmanage_invoicesrecord_manual_paymentmanage_mini_sessionsmanage_bookingsmanage_discount_codesreview_pending_orders
read_galleries and view_collection_analytics only read. Other workflows can include read actions such as list and get; writes ask for confirmation by default, configurable per tool. Review recipients, amounts and order details before approving. Features depend on your CloudSpot plan: Studio workflows require Full Suite features. Uploading photos and crop edits remain with you. CloudSpot does not email clients when a booking moves; arrange a separate message. Submitted print orders cannot be undone through the tools.
Optional local stdio bridge
Python 3.10 or newer is required, with no runtime dependencies. Clone this repository and configure a client that supports stdio:
{"mcpServers":{"cloudspot":{"command":"python3","args":["/absolute/path/to/cloudspot-mcp/cloudspot_agent.py"],"env":{"COTLET_API_KEY":"your-cotlet-key"}}}}
The local bridge lists seven browser helpers: cloudspot_guide, cloudspot_status, cloudspot_open, cloudspot_read, cloudspot_click, cloudspot_type and cloudspot_close. They forward to Cotlet.dev's shared browser tools and are distinct from the 17 hosted workflow capabilities. Call the guide first and close the browser when finished. Discovery works without a key; executing a tool requires your Cotlet.dev key and connected account.
python3 cloudspot_agent.py connect
python3 cloudspot_agent.py guide
python3 cloudspot_agent.py status
python3 cloudspot_agent.py serve
You can also build the included Dockerfile and pass COTLET_API_KEY as an environment variable.
Reference and access
Licensed under Elastic License 2.0. See LICENSE.