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., "@Breezeway MCP Create a maintenance task for the broken boiler at Harbor House and assign it to Alex."
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.
Yes, Claude, ChatGPT and other AI agents can work in your Breezeway account. Cotlet.dev connects your signed-in Breezeway account to AI agents so you can create, assign, comment on and approve property tasks.
Read tomorrow's Breezeway tasks for Harbor House. Show unassigned tasks and deadlines without changing assignments.
Create a maintenance task for the broken boiler at Harbor House and assign it to Alex.
Show the checklist and comments for the turnover task at Maple Cabin and summarize unresolved items.
Find unassigned cleaning tasks for Friday and propose suitable people without changing assignments.
Approve the completed inspection task for Harbor View after checking its checklist.
Related MCP server: AgentGo
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}This repo is a real MCP server. It speaks MCP over stdio, lists its Breezeway 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.
{"mcpServers":{"breezeway":{"command":"uvx","args":["breezeway-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t breezeway-mcp .
docker run -i --rm -e COTLET_API_KEY breezeway-mcpTools: breezeway_guide, breezeway_status, breezeway_open, breezeway_read, breezeway_click, breezeway_type, breezeway_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Python 3.10+, nothing else to install. From PyPI:
pip install breezeway-mcp # or run it once: uvx breezeway-mcp connect
breezeway-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 breezeway_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 breezeway_agent.py status # is Breezeway ready in your Cotlet.dev account
python3 breezeway_agent.py guide # Breezeway screens and sign-in link
python3 breezeway_agent.py read # open Breezeway, read the page, close the browser
python3 breezeway_agent.py tools # list Cotlet.dev tools
python3 breezeway_agent.py serve # start the stdio MCP server (same as no argument)Does Breezeway have an API?
Breezeway has a public REST API, but account holders request credentials through its developer form. Cotlet.dev works in your signed-in Breezeway account through a hosted connection, so you do not need a Breezeway API key.
How do I connect Breezeway to ChatGPT?
Add Cotlet.dev in ChatGPT with the connector URL https://cotlet.dev/mcp/v1/connect, sign in to Breezeway once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words.
Can I use Claude with Breezeway?
Yes. Add https://cotlet.dev/mcp/v1/connect as a custom connector in Claude, or use the Cotlet MCP server from Claude Code, and Claude can work with your Breezeway account.
Is there a Breezeway MCP server?
Breezeway has no official MCP server listed in its checked developer material. Cotlet.dev is a hosted MCP server that provides 13 Breezeway tools for ChatGPT, Claude and other AI agents.
Start free: https://cotlet.dev/signup?app=breezeway&utm_source=github&utm_medium=readme&utm_campaign=breezeway
Click a numbered element on the current Breezeway page.
Inputs: element (required).
Close the Breezeway browser session when the work is done, so credits stop running.
Inputs: no named parameters.
How to work in Breezeway (create, assign, comment on and approve property tasks): its screens and the sign-in link. Call this first.
Inputs: task.
Open a Breezeway page in your signed-in Cloud Browser (default https://app.breezeway.io) to work with create, assign, comment on and approve property tasks.
Inputs: url.
Read the current Breezeway page: its text and numbered buttons, links and fields.
Inputs: element.
Check that your Cotlet.dev account and Breezeway are ready: account, credits and Breezeway connection.
Inputs: no named parameters.
Type text into a numbered field on the current Breezeway page.
Inputs: text (required), element (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool maps to a distinct phase of a browser-automation loop (status, guide, open, read, click, type, close), so an agent can generally pick correctly. The only mild overlap is between breezeway_status (account/connection readiness) and breezeway_guide (how-to orientation), which both serve as entry points and could be confused at the start of a session.
All seven tools use the same breezeway_ prefix followed by a single lowercase verb or noun, matching a predictable pattern throughout. There are no mixed conventions or casing inconsistencies.
Seven tools is a tight, well-scoped set for a single-site browser automation surface, with no redundant entries. Each tool corresponds to a concrete step (session setup, observation, interaction, teardown) and earns its place.
The surface covers the full loop: connect/check, orient, open, read, click, type, close, which is enough for create/assign/comment/approve task workflows. Minor gaps exist around navigation beyond the default page, scrolling, and explicit keyboard submit, though these can mostly be worked around via clicking numbered buttons.
Breezeway MCP server for ChatGPT, Claude and any AI agent: list tasks, create task, assign task, add task comment, close task, approve task, reopen task and read task checklist in your own Breezeway account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Breezeway yourself; Cotlet does not store your password and you need no Breezeway API key. About the official Breezeway API: Breezeway has a REST API for properties, reservations, tasks and people, but you need API keys from a request form, and it has no official MCP server (checked 20 Oct 2026). Templates, task tags, subdepartments and supplies can only be created in the app. Setup and FAQ: https://cotlet.dev/integrations/breezeway-api-mcp-server
Buildium MCP server for ChatGPT, Claude and any AI agent: record lease payment, list outstanding balances, send text message, create task, add work order and send announcement in your own Buildium account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Buildium yourself; Cotlet does not store your password and you need no Buildium API key. About the official Buildium API: Yes, Buildium has an official REST API, the Open API, but only on the Premium plan (checked 27 Oct 2026). Buildium's developer guide says "To take advantage of the Buildium Open API you must have a Premium Subscription", and an administrator has to switch it on under Settings > Application settings > Api settings before anyone can create a key. Setup and FAQ: https://cotlet.dev/integrations/buildium-api-mcp-server
Rently MCP server for ChatGPT, Claude and any AI agent: list tours, get prospect details, update listing availability, create lock code and export leads in your own Rently account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Rently yourself; Cotlet does not store your password and you need no Rently API key. About the official Rently API: Rently has a public API for smart home devices and lock codes, but no on-demand API for leads, showings or listing status (checked 11 Oct 2026). Tour webhooks, lead data exports and partner credentials are set up by Rently staff, and the property feed is pulled once an hour. Setup and FAQ: https://cotlet.dev/integrations/rently-api-mcp-server
ServiceTrade MCP server for ChatGPT, Claude and any AI agent: list jobs, create appointment, release appointment to technicians, list deficiencies, create quote, submit quote and add comment to job in your own ServiceTrade account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ServiceTrade yourself; Cotlet does not store your password and you need no ServiceTrade API key. About the official ServiceTrade API: ServiceTrade has a full REST API with public docs and OAuth2 client-credentials sign-in, but no official MCP server (checked 23 Oct 2026). The API covers jobs, appointments, deficiencies and quotes, so the missing piece is the agent layer: you build and host the wrapper yourself. Setup and FAQ: https://cotlet.dev/integrations/servicetrade-api-mcp-server
