With this new offering, the company becomes the first accounts receivable (AR) platform to directly link live invoice-to-cash intelligence to leading AI assistants through the Model Context Protocol (MCP), Billtrust said in a Tuesday (July 21) news release.
“Finance teams can now query their live invoice-to-cash data directly from inside Microsoft Copilot and Claude, using plain language to get data-backed answers in seconds without logging into a separate platform or stitching data together from multiple sources,” Billtrust said.
Users can also get “structured, read-only access” in four domains: invoicing, payments, cash application and AR analytics, the company added, giving the example of a CFO asking AI to “Summarize our AR risk going into quarter end” and instantly getting an executive summary.
An AR manager can ask “Which accounts are trending late?” and get a ranked list according to outstanding balance and days overdue, without needing to open a single report.
Answers to those types of questions are gleaned from connected tools like enterprise resource planning (ERP) or customer relationship management (CRM) systems, the release said. It also uses Billtrust’s AR intelligence, which is trained on anonymized payment data from 13 million buyers and more than $1 trillion in yearly invoice volume.
“For 25 years, Billtrust has been building the largest payments intelligence network in B2B, and that history has always been our customers’ greatest advantage,” said Lee An Schommer, chief product officer at Billtrust. “What changes today is where that insight lives. Finance teams shouldn’t have to leave the AI workspace where they’re already making decisions. The Billtrust MCP Server puts AR data where it’s more accessible, so the answer is always one question away.”
PYMNTS spoke with Billtrust’s Schommer earlier this year about the strain facing traditional AR and ERP models. One of the clearest indicators that those models are under pressure is the increasing fragmentation of enterprise systems, the report said.
The notion of a single ERP instance governing the entire company has, in many cases, given way to a patchwork of platforms handed down through acquisitions or regional operations.
“On average companies are dealing with about three ERPs,” Schommer said. “You have data silos. And if the ERP can’t handle pulling together the data from these different systems … it just adds to the problem.”
For all PYMNTS B2B coverage, subscribe to the daily B2B Newsletter.
