About jobber-mcp-server
jobber-mcp-server gives MCP-compatible clients access to Jobber field-service data, including clients, jobs, invoices, and quotes. It supports operational queries and quote creation, and includes a mock mode for testing without a Jobber account.
Key features
- 01List and look up clients
- 02Retrieve job details and assignments
- 03Filter and inspect invoices
- 04Create client quotes with line items
- 05Test with mock data
Use cases
- 01Check today’s jobs and overdue invoices
- 02Review a client’s details and recent jobs
- 03Draft a quote while in the field
- 04Find unpaid invoices for follow-up
MCP support
Exposes Jobber client, job, invoice, and quote operations as tools for MCP clients. Mock mode supplies sample data without making Jobber API calls.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | Maximum number of clients to return (default 50). |
| isLead | boolean | No | If true, only leads. If false, only non-leads. |
| search | string | No | Substring to match against client name or email. |
Details
From the project READMEJobber MCP Server
An MCP server for Jobber — connect any MCP-compatible client to your Jobber field-service data.
What is this?
An MCP (Model Context Protocol) server that gives AI assistants and agents access to your Jobber data — clients, jobs, invoices, and quotes — through a clean, typed API.
Use it with Claude Desktop, Cursor, Windsurf, Cline, or any MCP-compatible client to ask questions about your business data, create quotes, and manage field-service operations through natural language.
Why use this?
- 6 built-in tools — clients, jobs, invoices, and quotes in one server
- Mock mode — try it instantly with fake data, no Jobber account needed
- Natural language queries — "show me overdue invoices" just works
- Quote creation — create and send quotes without opening Jobber
- Client lookup — find client details, contact info, and job history
- Works with every MCP client — Claude Desktop, Cursor, Windsurf, Cline, and more
Quick Start
Add to your MCP client config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"jobber": {
"command": "npx",
"args": ["-y", "jobber-mcp-server"],
"env": {
"JOBBER_ACCESS_TOKEN": "your_token",
"JOBBER_CLIENT_ID": "your_client_id",
"JOBBER_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Or try with mock data first (no Jobber account needed):
JOBBER_MOCK_MODE=true npx jobber-mcp-server
Get API credentials at Jobber Developer Portal.
Use it
Ask your AI assistant things like:
- "List all my clients"
- "Show me the details for client-101"
- "What jobs are assigned to Alex Reyes?"
- "Create a quote for Northwind Roofing: 2 hours of emergency repair at $150/hr"
- "Which invoices are overdue?"
Tools
| Tool | Description |
|---|---|
list_clients | List clients with optional search, lead filter, and limit |
get_client | Get a client by ID with contact info and recent jobs |
get_job | Full job detail: status, assignees, schedule, line items |
list_invoices | List invoices filtered by client and/or status |
get_invoice | Full invoice detail with line items and payment status |
create_quote | Create a new quote for a client with line items |
Use Cases
Daily Operations Check
"Show me today's jobs and any overdue invoices" — start your morning with a full picture of what needs attention. No more logging into Jobber's dashboard first thing.
Client Research
"What's the history with Northwind Roofing?" — pull up client details, recent jobs, and outstanding invoices before a site visit or sales call.
Quote Generation
"Create a quote for Mrs. Chen: gutter cleaning, 1 hour, $120" — draft and send quotes from the field without switching apps.
Invoicing Audit
"Show me all unpaid invoices over $500" — find overdue payments and follow up without manually filtering through Jobber's invoice list.
Field Service Reporting
"Summarize Alex Reyes' jobs this week" — generate performance summaries for team meetings or payroll without pulling reports manually.
Security
- OAuth credentials required — Jobber API uses OAuth2. Credentials are passed via environment variables, never logged.
- No local file access — does not read or write any files on your machine (unless you enable mock mode).
- No shell access — does not execute commands or spawn processes.
- Mock mode safe —
JOBBER_MOCK_MODE=trueuses fake data with no API calls to Jobber. - Open source — MIT licensed. Inspect the code at GitHub.
Troubleshooting
"Authentication failed" errors
Verify your JOBBER_CLIENT_ID, JOBBER_CLIENT_SECRET, and JOBBER_ACCESS_TOKEN are correct. Tokens expire — check the Jobber Developer Portal for fresh credentials.
"No data found" in mock mode
Make sure JOBBER_MOCK_MODE=true is set in your environment or MCP config. Mock mode creates sample clients, jobs, and invoices automatically.
Server won't start
Make sure Node.js 18+ is installed: node --version. If using npx, ensure npm is up to date: npm install -g npm@latest.
MCP client can't connect
Verify the config path is correct. Claude Desktop uses ~/Library/Application Support/Claude/claude_desktop_config.json on macOS and %APPDATA%\Claude\claude_desktop_config.json on Windows. Restart the client after config changes.
Slow responses
Jobber's GraphQL API has ~200-500ms latency. Complex queries (e.g., listing clients with full job history) may take longer. Use list_clients with a limit parameter to speed up initial queries.
Jobber API Setup
To use with your real Jobber account:
- Go to Jobber Developer Portal
- Create an app and get your
client_idandclient_secret - Complete OAuth flow to get an
access_token - Add credentials to
.envor MCP client config
Requirements
- Node.js 18+
- A Jobber account with API access, or use
JOBBER_MOCK_MODE=truefor testing
Development
git clone https://github.com/friendlygeorge/jobber-mcp-server.git
cd jobber-mcp-server
npm install
npm run build
npm run inspect # opens MCP Inspector for testing
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.