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, ChatGPT, Claude and other AI agents can work in your Service Autopilot account. Jobs, schedules, estimates and invoices in Service Autopilot can be handled through Cotlet.dev over MCP or REST.
Move rained-out visits to an open day.
Read each crew's route for the day.
Add clients with repeating jobs.
Turn site notes into estimates.
Invoice jobs and list what is unpaid.
Related MCP server: ServiceTitan MCP Server
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 Service Autopilot 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":{"service-autopilot":{"command":"uvx","args":["service-autopilot-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t service-autopilot-mcp .
docker run -i --rm -e COTLET_API_KEY service-autopilot-mcpTools: service_autopilot_guide, service_autopilot_status, service_autopilot_open, service_autopilot_read, service_autopilot_click, service_autopilot_type, service_autopilot_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 service-autopilot-mcp # or run it once: uvx service-autopilot-mcp connect
service-autopilot-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 service_autopilot_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 service_autopilot_agent.py status # is Service Autopilot ready in your Cotlet.dev account
python3 service_autopilot_agent.py guide # Service Autopilot screens and sign-in link
python3 service_autopilot_agent.py read # open Service Autopilot, read the page, close the browser
python3 service_autopilot_agent.py tools # list Cotlet.dev tools
python3 service_autopilot_agent.py serve # start the stdio MCP server (same as no argument)Does Service Autopilot have an MCP server or an API?
The live Service Autopilot page documents Cotlet.dev MCP and REST access for your signed-in account.
How does Cotlet.dev connect to Service Autopilot?
Sign in to Service Autopilot in your Cotlet Cloud Browser, then connect your agent over MCP or use the Cotlet.dev REST API.
What can an AI agent do in Service Autopilot?
It can read routes, manage jobs, work with estimates and list invoices through the tools documented on the live page.
How do I connect Service Autopilot to ChatGPT or Claude?
Add https://cotlet.dev/mcp/v1 in ChatGPT or Claude, then use your connected Service Autopilot account.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Run a home-service business from your AI: jobs, customers, invoices, estimates, texts.
Run a service business from your AI agent: CRM, leads, scheduling, invoicing, jobs and more.
Manage jobs, customers, scheduling, estimates and invoices for a field service business.
Job management for service companies: look up, book, tag, assign and note jobs from your AI.
