Integrations · Accounting

Automate e-conomic work with your agents

Maplith maps how e-conomic’s customers, booked invoices and lines, products, and entries join your web shop, CRM, payments, helpdesk, ads and spreadsheets, so your agent knows where each thing is and how far to trust each join.

Share e-conomic’s exports today; Maplith maps them from there.

WayStatusWhat it means
Export filesAvailableCSV exports: the current and previous financial year. The path to start with.
Example flows

What your agents do with e-conomic and Maplith

What starts the work, what your agent does with Maplith, and how it ends. Each flow uses the e-conomic data and joins described below.

01

A shipped order with no booked invoice

Trigger: Your bookkeeper wants to know whether every order the shop shipped last month was invoiced in e-conomic.

With Maplith:

  1. Route: route from the shop order to the booked invoice in e-conomic by the order reference, and says how much Maplith trusts that hop.
  2. The map: get_object on the booked invoices says the order reference sits in the field e-conomic calls other reference, with the rate a scan measured for that join. The agent lists last month’s orders in your shop with its own access.
  3. Findings: Where the last scan of the exports saw orders with no invoice against them, a finding names the gap, with its evidence and a recommendation.
  4. The action gate: request_action for a task for the bookkeeper with last month’s order references and the field to match them on in e-conomic, decided by the key’s policy. The bookkeeper checks and books them in e-conomic.
  5. Record and value: record_action records that the list reached the bookkeeper, and how the month closed.

Result: The bookkeeper checks last month’s orders against e-conomic by the reference it books them under.

02

Which e-conomic customer a CRM company is

Trigger: Before chasing an invoice, sales asks which customer in e-conomic a company in the CRM is.

With Maplith:

  1. Ask: ask: “how do e-conomic’s customers tie to companies in the CRM?” The answer cites the joins it rests on: the CVR number of a business customer first; a match by name is weaker.
  2. Route: route from the CRM company to the e-conomic customer by CVR number, then on to its booked invoices by customer number.
  3. The map: get_object on the CRM company says which field holds its CVR number; the agent reads that field in the CRM with its own access.
  4. The action gate: request_action for a task for the bookkeeper: the CRM company, its CVR number, and the route to its booked invoices to look up in e-conomic.
  5. Record and value: record_action records who got the task and what they found.

Result: The bookkeeper finds the company in e-conomic by the number both systems share, not by a name that may differ.

03

A payout the ledger entries do not add up to

Trigger: A payout from your payment provider is in the bank, and the entries in e-conomic for that day do not seem to add up to it.

With Maplith:

  1. Route: route from the payout to e-conomic’s entries by date and amount, and from the entries to the invoices behind them by voucher number.
  2. The map: get_object on the entries says they meet a payout only by date and amount, with no id both sides carry. The agent reads the payout’s balance transactions in Stripe with its own read access.
  3. Findings: Where the last scan of the exports found payouts the entries do not add up to, a finding with its evidence and a recommendation.
  4. The action gate: request_action for a task for the bookkeeper with the payout, what it is made of in Stripe, and the date and amount to look for in e-conomic’s entries.
  5. Record and value: record_action records that the task went out, and what the bookkeeper found.

Result: The bookkeeper checks the payout against e-conomic’s entries with Stripe’s side of it already broken down.

Steps that use request_action or record_action need an agent key that may act; a read-only key reads the map.

Access

How it connects

Through access you already have. Maplith holds no e-conomic credential and never writes there.

  1. Export from e-conomic: CSV, the current and previous financial year. The guide has the steps.
  2. Upload the files in your workspace, or let your assistant send them to Maplith over MCP.
  3. Maplith builds the map and deletes the files again.

What Maplith never reads or does

  • e-conomic itself: Maplith holds no e-conomic credential and never signs in to it.
  • Anything that changes e-conomic: Maplith never writes there.
  • What you leave out: you decide what an export contains.

Datasets that make a good map

Customers

One customer with number, group, address and payment terms.

  • customer number
  • CVR number of a business customer
  • customer group
  • customer email (Maplith tries to mask it)

Booked invoices and lines

One booked sales invoice, with one row per invoice line.

  • invoice number
  • customer number
  • product number
  • other reference / order reference
  • invoice date
  • due date

Products

One product or service with number, group and sales account.

  • product number
  • product group

Entries

One booked line on one account, with date, voucher number and amount.

  • account number
  • voucher number
  • entry date
  • VAT code

Chart of accounts

One account in the ledger, with number, name, type and VAT code.

  • account number
  • account type
  • VAT code

Suppliers

One supplier with number, group and payment terms.

  • supplier number
  • CVR number of a business supplier
  • supplier group

The narrowest access e-conomic offers (none of it is read-only)

  • Sales (customers, invoices, orders, products)
  • Bookkeeping (accounts, accounting years, journals, entries)

The superuser of the e-conomic agreement, or the external accountant or bookkeeper added as an administrator. e-conomic app roles have no read-only role, so pick the narrowest role that covers the data.

Checked against e-conomic’s documentation on 20 October 2026. Sources and export steps: Read e-conomic into Maplith.

FAQ

Questions about e-conomic and Maplith

Does Maplith copy my e-conomic data?
No. Maplith keeps metadata about your data: which datasets e-conomic holds, their fields, and how they join your other systems. It does not keep copies of the records. What you share is read for a build and then deleted. The map may quote example values and evidence.
Which e-conomic access does Maplith need?
None: Maplith holds no e-conomic credential. You share e-conomic’s exports; the superuser of the e-conomic agreement, or the external accountant or bookkeeper added as an administrator, can make them. e-conomic offers no read-only role: if a tool of yours reads e-conomic instead, give it the narrowest role that covers the data, such as Sales or Bookkeeping, never Superuser.
Which AI assistants work with Maplith and e-conomic?
Any assistant that speaks MCP, such as Claude, ChatGPT or one you build, connects to Maplith by signing in or with an agent key. You share e-conomic’s exports with Maplith, and your agent reads the map. Connect your own agent
Where is my e-conomic data processed?
In the EU, except model inference. Hosting, database and file storage are in the EU. Model inference runs in the United States under standard contractual clauses: to build the map, samples of the files and, in the findings step, whole files are sent to Maplith’s model provider, which deletes them within 30 days. Security states the details.
Does Maplith change anything in e-conomic?
No. Maplith holds no e-conomic credential and never writes to e-conomic: it reads only the exports you share. A change in e-conomic stays with the people who keep your books there.
What about customer emails and other personal data in e-conomic?
e-conomic’s customers hold customer emails and addresses. Maplith tries to mask email local parts and the names in an export’s own name columns (on by default; an admin can switch it off). It is a best-effort safeguard, not a guarantee, and it does not cover addresses: leave out what must not be processed.
Does e-conomic have an MCP server Maplith can read?
No official one is confirmed. Several community MCP servers for e-conomic exist, but none is from Visma e-conomic. Its own complete export gives every register as a CSV file with all fields in one go, filtered by date, and that is what Maplith maps.
Which e-conomic data makes a good map?
Customers, booked invoices and lines, products, entries, chart of accounts and suppliers. For a first map, the exports cover the current and previous financial year.

Map e-conomic with the rest of your business