How to connect BigChange to Claude
BigChange has no Claude connector of its own, so asking Claude about your jobs, engineers, invoices or fleet still means exporting a report and pasting it in. This guide covers how to connect BigChange to Claude properly, using Tugger and its built-in MCP server, so you can ask "which jobs are overdue and who's assigned" or "what's our first-time fix rate by job type" and get an answer from your own BigChange data. Setup takes a Tugger account, an API key from the BigChange Developer Portal and about ten minutes.
What you can ask once BigChange is connected to Claude
Tugger syncs your BigChange data on a schedule into a managed data warehouse, then exposes that warehouse to Claude through a read-only MCP server. Claude queries the warehouse, never BigChange itself, so nothing Claude does can change a job, an invoice or a schedule.
Typical questions:
- Which jobs are past their due date and not completed, by engineer and customer?
- What is our first-time fix rate by job type over the last six months?
- What did we invoice by month and by department this year, and how much is sent but unpaid?
- What is each engineer's utilisation, actual hours against planned, for the last quarter?
- Which quotes over £2,000 have been sent but not accepted for more than 14 days?
- Which vehicles have an MOT, service or insurance due in the next 30 days?
- Which service agreement assets are overdue a visit?
Claude writes the query, runs it and explains the result. You can follow up in the same conversation, ask for a chart, or ask Claude to build a dashboard and bake the figures in.
What you need
- A Tugger account. You can start a free 10-day trial if you don't have one.
- A BigChange account with access to the BigChange Developer Portal and permission to create API keys.
- A Claude plan that supports connectors (Pro, Max, Team or Enterprise).
Step 1: add the BigChange connector in Tugger
- Log in to Tugger, click Add Connector and choose BigChange.
- Give the connector a name, such as "BigChange", and choose how far back you want history to sync from. Further back means more data and a longer first sync.
- Leave the three credential fields (Customer Id, Client Id, Client Secret) blank for now and keep this tab open.
Step 2: create an API key in BigChange
Tugger connects to BigChange with three credentials, all from the BigChange Developer Portal.
- Sign in to the BigChange Developer Portal and open API Key Management.
- Note your Customer ID. It's shown at the top of the page in the line "You can create multiple API keys for your customer ID".
- Click Create new API Key and give it a name, such as "Tugger".
- Under Scopes, select the read scopes only: contacts:persons:read, contacts:read, finance:read, jobs:read, notes:read, resources:read, stock:read, users:read, vehicles:read, webhooks:read and worksheets:read. Don't select any write scopes; Tugger only reads.
- Click Register.
- On the API Key Management page, open the three-dot menu next to the new key, choose Create new credentials, and confirm. Copy the Client ID and Client Secret straight away; the secret isn't shown again once you leave the page.
Back in Tugger, paste the Customer ID, Client ID and Client Secret into their fields and click Save Settings. Tugger verifies the connection and starts the first sync. After that it refreshes every day at 08:00 UK time by default, which you can change in Tugger, and you'll get an email when the data is ready.
Step 3: add Tugger's MCP server to Claude
- In Tugger, open AI Insights and copy your MCP server URL.
- In Claude, go to Settings, then Connectors.
- Choose Add custom connector.
- Name it "Tugger" and paste the MCP server URL.
- Click Add, then Connect, and sign in to Tugger when prompted.
In any new chat, open the connectors menu and switch Tugger on. Claude can now see the tables Tugger has synced from BigChange.
Step 4: ask your first question
Start with something simple to confirm the connection is working:
"Show me jobs completed per week for the last eight weeks, split by job type."
Claude will find the job and job type tables, run the query and return the result. From there you can ask follow-ups, request a chart, or ask Claude to explain how it built the query.
What syncs from BigChange
Tugger brings across the full job lifecycle plus the finance, stock, fleet and asset tables you need to report on it properly.
| Area | Data |
|---|---|
| Jobs | Jobs and job groups with type, status, contact, resource and vehicle; status history; line items; constraints; flags and flag history |
| Contacts and people | Customers, sites and suppliers with groups and hierarchy; named persons; site access hours; consent history |
| Resources and users | Engineers and field workers with groups; office users and roles |
| Finance | Invoices and line items with payment status; quotes and line items; purchase orders and line items; nominal, department and VAT codes |
| Sales | Sales opportunities with stage, probability and owner; opportunity line items |
| Stock | Stock definitions and categories, stock items by location (site or vehicle), stock movements, job stock, suppliers |
| Fleet | Vehicles with MOT, service and insurance dates, costs and emissions |
| Worksheets | Worksheet templates, questions and the answers captured on jobs |
| Asset management | Assets and categories, service agreements and schedules, services and service attempts; needs the Asset Management module |
| Notes | Notes with type, owner and progress history |
If you need something that isn't listed, ask us. Tugger's connectors are extended based on customer requests.
Why a warehouse rather than a direct connection
You could point an automation tool or a third-party MCP server at BigChange's API directly. Three reasons to put a warehouse in between.
- Read-only by design. Claude queries a copy, so a mistyped question can't reschedule a job or change an invoice. The BigChange API key Tugger uses has read scopes only.
- Full history, consistent answers. Questions such as first-time fix rate or utilisation by engineer need every job and every status change, not one API page at a time. The tables and relationships are fixed, so the same question gives the same answer next week.
- The rest of your systems are there too. Once BigChange is in the warehouse alongside Xero, QuickBooks or Breathe HR, Claude can match BigChange invoices to accounts payments, or field hours to payroll, in one question.
Tugger is UK-based and ISO 27001:2022 certified. Your warehouse is hosted on Azure, in the UK by default or any Azure region on request, and the same warehouse feeds Power BI and Tableau if you use them. Tugger's MCP server works with Claude, ChatGPT and Gemini.
Related guides
- What is an MCP server?
- How to connect ServiceM8 to Claude
- Simpro MCP server guide
- How to connect Xero to Claude
- How to connect Breathe HR to Claude
- How to build a Claude dashboard
Get started
Connecting BigChange to Claude with Tugger takes no code and no faff. Try Tugger free for 10 days or book a demo and we'll walk through it with your own BigChange data.
