Jobkeepr MCP server

What it does

This server connects Jobkeepr field service management software to AI assistants, allowing you to read and manage jobs, customers, scheduling, estimates, invoices, and payments for a small contractor business. It works with Claude, ChatGPT, and other MCP clients via a hosted remote endpoint or stdio bridge.

• Query your schedule and job history to answer questions like "What's on my schedule tomorrow?" or "Which service made the most money last month?"
• Create and manage jobs and customers, such as booking a technician for a specific time or adding a new customer to your system.
• Track financial data including estimates, invoices, payments, and line items across jobs for reporting and analysis.

Tools this server exposes

Tool	Does
get_business_context	Retrieve business name, timezone, working hours, and today's date with resolved date ranges.
get_jobs	Search and filter jobs by date, status, customer, type, or source.
get_customers	Search customers with optional job counts and financial totals.
get_schedule	View scheduled jobs and open time slots.
get_estimates	Retrieve estimates and their status.
get_invoices	View invoices and unpaid balances.
get_payments	See payments received.
get_line_items	Analyze line items across jobs for margin and service mix analysis.
get_reference_data	Access job types, job sources, and the price catalog.
create_job	Book a new job for a customer.
create_customer	Add a new customer to your system.
create_estimate	Create an estimate for a job.
create_catalog_item	Add a service or product to your price catalog.
add_line_items	Add billable line items to a job.
set_job_source	Record where a job originated from.
reschedule_job	Move a job to a different date or time.
cancel_job	Cancel a scheduled job.
close_jobs	Mark one or more jobs as complete.

Before you enable it

An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.