Docs: System guides
Read Billy into Maplith
On this page
Best path
Recommended: export files. No official MCP server or client connector was found, and Billy's export menu gives the posting journal, contacts, products and chart of accounts as files for a chosen period. A Billy access token gives full read and write access, so a file export is the safer read-only path.
Try the paths in this order:
- Your agent fetches it, with the access you already gave it. No named connector is confirmed: check the tools your agent already has. Your agent checks whether it already has a Billy tool it trusts, and if so reads only the chart of accounts, contacts and products. The posting journal and invoice history should come from the export.
- Maplith reads an MCP server you already run. No official MCP server confirmed. Community MCP servers for Billy exist on GitHub, but none is from Billy. Maplith reads a server that serves MCP resources and takes a token a person types under Data sources › Systems, such as one your IT runs for a database.
- Export files, the fallback that always works. See the export steps below.
Datasets that make a good map
| Dataset | One row is | Key columns | Joins to |
|---|---|---|---|
| Contacts (Kontakter) | One customer or supplier. | contact number, CVR number of a business customer, EAN number, customer or supplier flag, contact email (Maplith tries to mask it) | CRM companies by CVR number; webshop customers by email; invoices and bills by contact. |
| Invoices (Fakturaer) | One sales invoice or credit note with its lines, totals, dates and payment status. | invoice number, contact number, product number on each line, invoice date, due date | Payment providers, webshop orders and bank lines by invoice number; Contacts by contact number; Products by product number. |
| Products (Produkter) | One product or service that can be put on an invoice. | product number, product name | Webshop and inventory products by product number (SKU); invoice lines by product number. |
| Posting journal (Posteringsjournal) | One booked line on one account, with date, transaction number and amount. | account number, transaction number, date | Chart of accounts by account number; bank statements and payouts by date and amount; invoices and bills by transaction. |
| Chart of accounts (Kontoplan) | One account in the ledger, with number and name. | account number, account name | Posting journal by account number. |
Columns are named, never their values. Maplith tries to mask personal data such as email addresses, but that is best effort: you decide what goes in.
The access to give
Who usually has the rights: The owner of the Billy account; only the owner manages users. An invited accountant (Revisor role) can see the books but cannot manage users.
Choose the narrowest access that covers the data:
- Access token (full access to one company; Billy offers no read-only scope)
- Revisor role
- Begrænset admin role
Where to click:
- Log in to Billy
- Settings
- Access tokens
- Create access token
- Give it a clear name and click Save
- Hover over the token and click the magnifier to copy it
A key or token made here stays in the tool that reads the system, never in a chat. Maplith asks for one only under Data sources › Systems in the app.
Export steps
Format: CSV or XLS Date range: The current and previous financial year
- Click Rapporter, then Eksport.
- Choose the list you need: Posteringsjournal, Kontospecifikation, Kontakter, Produkter or Kontoplan.
- Choose the period and the file type (CSV or Excel) and click Eksporter.
- For invoices and payments per customer, open Regnskab, Eksport and download Kunde- eller leverandørkontokortet.
- The Backup shortcut under Rapporter, Eksport downloads every transaction as a PDF with its vouchers; it is an archive, not a data file.
How much data
About 10–300 invoices; 100–2,000 postings a month (an estimate). Estimate for a small company, not a measured figure: Billy is aimed at micro and small companies, and each invoice or bill creates a few postings.
An agent that reads rows through a chat reads every one of them, about one token per four characters. Above a few thousand rows a dataset, or for a daily refresh, an MCP server or an export is the better path.
Always
- Read-only, and never a credential sent to Maplith through a chat.
- The same recent period, a few months, from every system.
- You decide what goes in.
Sources
Written from public documentation, last checked 2026-10-08: