Jobber MCP Server
Enables AI assistants to access and manage Jobber field-service data including clients, jobs, invoices, and quotes through natural language interactions.
README
Jobber 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.
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 |
Quick Start
1. Install
npm install jobber-mcp-server
Or run directly with npx:
npx jobber-mcp-server
2. Configure
Create a .env file or set environment variables:
# Required: Jobber API credentials
JOBBER_CLIENT_ID=your_client_id
JOBBER_CLIENT_SECRET=your_client_secret
JOBBER_ACCESS_TOKEN=your_access_token
# Optional: use mock data for testing (no Jobber account needed)
JOBBER_MOCK_MODE=true
3. Add to your MCP client
Add to your MCP client config (e.g. Claude Desktop's 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 with a local install:
{
"mcpServers": {
"jobber": {
"command": "node",
"args": ["/path/to/jobber-mcp-server/dist/index.js"],
"env": {
"JOBBER_MOCK_MODE": "true"
}
}
}
}
Demo
Try it instantly with mock data — no Jobber account required:
JOBBER_MOCK_MODE=true npx jobber-mcp-server
Then ask your MCP client:
- "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?"
Example output
Client list:
Found 3 clients:
**Marlene Okonkwo** _(active)_ — id: client-101
- Email: marlene@example.com
- Phone: +1-555-0142
- Address: 412 Birchwood Ln, Boulder, CO, 80302
- Lifetime spend: $4,280.00
**Northwind Roofing LLC** _(active)_ — id: client-102
- Email: ops@northwindroofing.example
- Phone: +1-555-0177
- Address: 8800 W Industrial Blvd, Denver, CO, 80221
- Lifetime spend: $28,400.00
- Outstanding balance: $1,200.00
**Devon Park** _(lead)_ — id: client-103
- Email: devon.park@example.com
- Phone: +1-555-0193
Quote creation:
✅ Created quote **Q-0072** for Northwind Roofing LLC
## Quote Q-0072 — Emergency repair — 2 hours
- **Status:** awaiting_response
- **Client:** Northwind Roofing LLC _(client-102)_
- **Created:** 2026-06-05 12:00 UTC
**Line items:**
| # | Item | Qty | Unit | Total |
|---|------|-----|------|-------|
| 1 | Emergency repair | 2 | $150.00 | $300.00 |
**Subtotal:** $300.00
**Total:** $300.00
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
The server uses Jobber's GraphQL API (https://api.getjobber.com/api/graphql).
Architecture
┌──────────────┐ stdio (JSON-RPC) ┌──────────────────┐
│ MCP Client │ ◄──────────────────────► │ jobber-mcp- │
│ (Claude, │ │ server │
│ Cursor, │ │ │
│ etc.) │ │ ┌────────────┐ │
└──────────────┘ │ │ Mock Data │ │
│ │ (testing) │ │
│ └────────────┘ │
│ │ │
│ ┌─────▼──────┐ │
│ │ Jobber API │ │
│ │ (GraphQL) │ │
│ └────────────┘ │
└──────────────────┘
Development
git clone https://github.com/nova-research/jobber-mcp-server.git
cd jobber-mcp-server
npm install
npm run build
npm run inspect # opens MCP Inspector for testing
Use Cases
- Field service operators — Ask your AI assistant about today's jobs, overdue invoices, or client history
- Office managers — Create quotes and check job status without opening Jobber
- AI agents — Automate follow-ups, generate reports, or trigger workflows based on Jobber data
- Accounting integration — Pull invoice data into AI-powered financial analysis
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。