We use cookies to improve your experience and for marketing. View our Cookie Policy for more information.

Ask Claude About Reconciliation, Forecasts, and Debt

Author
Lukas Linden Malmberg
Published
November 20, 2026
Last Update
November 20, 2026
Claude and Atlar app icons above the link claude.ai/directory/atlar, with Claude comparing October's forecast against actual closing cash from Atlar data.

Key takeaways

  1. Atlar's Model Context Protocol (MCP) connector now gives Claude access to reconciliation, forecast accuracy, debt schedules, benchmark rates, bank connections, users, and scheduled reports, alongside accounts, balances, transactions, and forecasts.
  2. Claude can show which receipts are still outstanding and what Atlar suggests matching them to, how close last month's forecast came to actuals, and the next interest payment on a floating-rate facility.
  3. The new lookups are read-only and run with the connected user's role, an admin decides whether the connector can also take actions, and every query is logged in Atlar's audit trail.
  4. The MCP connector is one of three ways to use AI with Atlar, alongside agentic workflows for recurring work and Ask Atlar for ad-hoc questions inside the platform.
  5. Read access and write actions will keep expanding, while approving payments stays with people by design.

Through Atlar's Model Context Protocol (MCP) connector, Claude can now see much more of the platform. Alongside accounts, balances, transactions, and forecasts, it can read reconciliation, forecast accuracy, debt schedules, benchmark rates, bank connections, users, and scheduled reports.

Finance teams use the connector for much more than looking up balances. Storytel's treasury manager, for example, builds the company's monthly treasury report in Claude from live Atlar data.

Reconciliation, forecasting, and debt

Claude can see reconciliation matches, suggested matches, and outstanding transactions, along with the rules and configurations behind them. Ask why a payment is still outstanding or which invoices a receipt was matched to, and the answer comes from the same reconciliation your accounting team works in.

Claude chat showing a table of four receipts over €50,000 outstanding for 8 to 15 days, with the counterparty, date received, amount, and Atlar's suggested invoice match for each.
Claude listing receipts over €50,000 that have been outstanding for more than a week, with the invoices Atlar suggests matching them to.

Forecast configurations and backtesting results show Claude how close last month's forecast came to actuals, and in which weeks it drifted.

Claude chat with a line chart of forecast versus actual closing cash for October, showing the forecast above actual every week and €2.2 million (5.0%) too high by week four.
Claude comparing October's four-week forecast with actual closing cash, week by week.

For debt, Claude pulls loan and facility settlements alongside benchmark rates and fixings such as EURIBOR and SOFR, and can work out the next interest payment on a floating-rate facility.

Claude chat showing a €25 million revolving credit facility with €12 million drawn, the 3M EURIBOR fixing, margin, and all-in rate, and a next interest payment of €126,653.33 due 31 December 2026.
Claude working out the next interest payment on a revolving credit facility from the latest EURIBOR fixing.

The connector also covers entities, pending transactions, direct debit batches, GL accounts, vendor bank accounts, bank connections, users and invitations, scheduled reports, and your own notifications.

Why coverage matters

An AI model can only answer well when it can see everything the answer depends on. Today's cash position needs balances. Explaining why the position moved needs pending transactions, reconciliation, and the forecast it was measured against. Every area Claude can't reach sends someone back to a dashboard or a spreadsheet export, and the conversation stops there.

We've argued before that models are rarely the bottleneck in finance, and that the data and tools around them decide what's possible. In Atlar, that data comes from bank connections we build and maintain ourselves, across banks in over 100 countries. It's standardized before Claude sees any of it.

See Atlar in Action

Get a live walkthrough tailored to your team.

Book a demo

The same controls as the dashboard

The new lookups are read-only. They run as the user who connected Claude, with that user's role. Claude can't see anything the role can't see in Atlar, an admin decides whether the connector can only read or also take actions, and every query is recorded in Atlar's audit trail. Customer data is never used to train external models.

Three ways to use AI with Atlar

The MCP connector is one of three ways finance teams work with AI in Atlar, and each suits a different kind of work.

  • Agentic workflows run recurring work on a schedule, such as a daily cash report checked against treasury policy or a morning review of upcoming rate resets and maturities. Each workflow recommends actions for someone to approve.
  • Ask Atlar, the assistant built into the platform, handles ad-hoc questions and simple actions, such as how balances have developed over the past year or drafting a loan facility from an uploaded agreement.
  • The MCP connector brings Atlar into the AI tools teams already work in, such as Claude and ChatGPT, where treasury data sits next to their documents and other connected apps.
The Atlar dashboard on an iPad, next to the Ask Atlar assistant summarizing how balances developed over the past 12 months.
Ask Atlar answering an ad-hoc question inside the platform, from the same live data Claude reads through the connector.

What comes next

Read access will keep expanding, with the approvals queue, payment audit trails, and receivables and payables aging next. Claude will also take on more of the work itself, such as logging loan and facility activity, uploading forecast estimates in bulk, and updating forecast structures. All of it will go through the same permissions and approval chains. Approving payments will stay with people, by design. Admins will also be able to approve other AI tools their teams use, beyond Claude and ChatGPT.

Getting started with Atlar's MCP connector

Atlar is listed in Claude's directory, and teams can connect a demo account before their own. The setup guide covers admin settings and access levels.

AI-first companies like Lovable and Parloa run treasury on Atlar, as do listed companies such as Storytel and Bandwidth. To see the connector against your own data, request a demo or get in touch with our team.

Lukas Linden Malmberg
Lukas leads product at Atlar alongside CPO Joel Wägmark. He previously worked in product at Planhat.

Frequently asked questions

What can Claude access through Atlar's MCP connector?

Accounts, balances, transactions, and forecasts, plus reconciliation matches and outstanding items, forecast configurations and backtesting results, loan and facility settlements, benchmark rates and fixings, entities, bank connections, users, scheduled reports, and notifications.

How do I connect Atlar to Claude?

Find Atlar in Claude's connector directory, click Connect, and approve access in Atlar. Teams can try it on a demo account first, and the setup guide covers admin settings and access levels.

What controls apply when Claude uses Atlar data?

Claude runs as the user who connected it, with that user's role, so it can't see anything that role can't see in Atlar. An admin decides whether the connector can only read or also take actions, and every query is recorded in Atlar's audit trail. Customer data is never used to train external models.

How is the MCP connector different from Atlar's own AI?

Agentic workflows run recurring work on a schedule inside Atlar, and Ask Atlar handles ad-hoc questions in the platform. The MCP connector brings the same data into the AI tools teams already use, such as Claude and ChatGPT.

What's coming next for the connector?

Read access to the approvals queue, payment audit trails, and receivables and payables aging, and more actions such as logging loan and facility activity and updating forecasts, all through the same permissions and approval chains. Approving payments stays with people.

Get fresh insights, monthly.

You can unsubscribe anytime.

Read more

November 18, 2026
•
Product News

AI Categorization Writes Your Cash Flow Rules

Atlar's AI categorization builds your cash flow categorization rules from a few labeled transactions, ready to review before anything goes live.

November 18, 2026
•
Product News

Atlar and Stacks Give AI Close Agents Complete Bank Data

Stacks, the agentic AI platform for enterprise finance, is integrating Atlar's bank connectivity, so its AI agents can reconcile and close the books from complete bank data.

November 3, 2026
•
Product News

AI-Native Debt Management Saves Neko Health 2 Days a Month

Atlar's debt management is now running at Neko Health, with AI agents that set up loans from the agreement and keep an eye on them once they're live.

See Atlar in action.

Enter your work email to watch a live product demo.

Thanks, you will receive an invite email soon.
Oops, something went wrong. Try again with your work email.
Forecasting screenshot comparing net cash across scenariosCircular headshot photos of three team members

See Atlar in Action

Get a live walkthrough tailored to your team.

Book a demo