Billtrust links receivables data to Copilot and Claude

Billtrust has introduced a server that connects live accounts receivable data with Microsoft Copilot and Claude, extending invoice-to-cash analysis into AI assistants used by finance teams. The company said in a July 21 release that the Billtrust MCP Server gives users structured, read-only access to information across invoicing, payments, cash application and AR analytics.

Billtrust described the product as the first direct connection between an AR platform and major AI assistants through the Model Context Protocol, a framework used to link AI systems with external data and tools. In practice, the company said, finance staff can ask questions in ordinary language inside Copilot or Claude and receive answers drawn from current invoice-to-cash records, without separately entering Billtrust or manually combining reports from several systems.

The release gave examples of how the tool could be used. A chief financial officer could ask for a summary of accounts receivable risk before quarter-end and receive an executive-level overview, according to Billtrust. An AR manager could ask which customers are becoming late payers and get a list ranked by unpaid balances and the number of days overdue.

The answers are based on connected systems such as enterprise resource planning and customer relationship management platforms, the company said. Billtrust also said the server uses its own AR intelligence, which has been trained on anonymized payment information from 13 million buyers and more than $1 trillion in annual invoice volume.

Lee An Schommer, Billtrust’s chief product officer, said in the release that the company’s payments intelligence network has been built over 25 years. “What changes today is where that insight lives,” Schommer said, adding that finance teams should not have to leave the AI tools where they are already making decisions.

The launch comes as many companies are dealing with more fragmented finance technology. In an earlier interview with PYMNTS, Schommer said traditional AR and ERP models are facing pressure because many organizations no longer operate from a single ERP system. Acquisitions and regional operating structures have left some businesses working across multiple platforms, according to the report.

Schommer told PYMNTS that companies deal with about three ERPs on average. That creates data silos, she said, and can worsen the problem when an ERP system cannot bring together information from different sources.

For finance departments, the product targets a recurring operational issue: receivables data often sits across billing systems, payment platforms, ERPs and customer databases. Billtrust’s approach is to let AI assistants query those connected records while limiting the interaction to read-only access, so users can retrieve analysis without changing underlying accounting or payment data through the assistant.

Billtrust did not disclose pricing or customer adoption figures in the release.

This story draws on original reporting from PYMNTS.