This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Yes, Claude, ChatGPT and other AI agents can work in your RazorSync account. RazorSync documents an API for developers, but we found no official RazorSync app in ChatGPT's or Claude's directory. Cotlet.dev connects your own signed-in RazorSync account to any AI agent, so you can ask in plain words and the AI schedules jobs, prepares invoices and follows up on unpaid bills for you.
Create a work order for Mike Chen at 42 Elm Street, AC not cooling, and assign it to Carlos for Tuesday at 9 am.
Turn yesterday's completed work orders into invoices and email them to the customers.
Which invoices are more than 30 days unpaid? List the customer, amount and due date.
Send a friendly payment reminder to every customer with an open invoice over $500.
Show me Thursday's schedule per technician and move Dave's 3 pm job to Friday at 8 am.
Related MCP server: housecallpro-mcp
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 RazorSync 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":{"razorsync":{"command":"uvx","args":["razorsync-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t razorsync-mcp .
docker run -i --rm -e COTLET_API_KEY razorsync-mcpTools: razorsync_guide, razorsync_status, razorsync_open, razorsync_read, razorsync_click, razorsync_type, razorsync_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 razorsync-mcp # or run it once: uvx razorsync-mcp connect
razorsync-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 razorsync_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 razorsync_agent.py status # is RazorSync ready in your Cotlet.dev account
python3 razorsync_agent.py guide # RazorSync screens and sign-in link
python3 razorsync_agent.py read # open RazorSync, read the page, close the browser
python3 razorsync_agent.py tools # list Cotlet.dev tools
python3 razorsync_agent.py serve # start the stdio MCP server (same as no argument)Does RazorSync have an API?
RazorSync documents an API for customers, work orders, scheduling, invoices and payments, but the token comes only from RazorSync support and needs a developer. Cotlet.dev works in your own signed-in RazorSync account instead, so your AI agent can open, schedule and invoice work orders.
How do I connect RazorSync to ChatGPT?
Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to RazorSync once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no RazorSync API key.
Is there a way to use Claude with RazorSync?
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 RazorSync account.
Is there a RazorSync MCP server?
RazorSync has no official MCP server and no official app in ChatGPT or Claude (checked November 2026). Cotlet.dev is a hosted RazorSync MCP server that works in your own account, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.
Start free: https://cotlet.dev/signup?app=razorsync&utm_source=github&utm_medium=readme&utm_campaign=razorsync
This server cannot be deployed
Run a service business from your AI agent: CRM, leads, scheduling, invoicing, jobs and more.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Run a home-service business from your AI: jobs, customers, invoices, estimates, texts.
Run field service from Claude, ChatGPT or Copilot: dispatch, billing, customer messages, photos, and change the software itself, with a confirm step before every change. This address is the India region; US East, Canada, Norway and NZ addresses are at fieldproxy.ai/mcp.