As healthcare organizations consider leveraging agent artificial intelligence technology, Wolters Kluwer Health is developing foundational capabilities to support automation of medication workflows and prescription processes with AI agents.
The company deployed Medi-Span Expert AI to provide “AI-enabled” expert-curated medicines to digital health technology developers. The company provides select AI developers with a Model Context Protocol (MCP) server designed to reduce development timelines and complexity for customers by connecting third-party AI applications and agents to Medi-Span content.
Medi-Span provides a suite of embedded drug databases and data solutions that support medication-related decision-making across healthcare settings, from hospital and emergency room settings to pharmacy dispensing systems. According to Christian Hartman, vice president of product innovation, pharmacy and medical technology solutions at Wolters Kluwer Health, Medi-Span is widely used by pharmacy benefit managers, health plans, retail pharmacies, electronic health record vendors, digital health technology and healthcare organizations to support prescription management, drug safety, claims processing and drug pricing.
“MCP, which we are announcing today, provides the foundational functionality for medication workflow automation, providing structured, evidence-based medication intelligence through the MCP server that teams need as they build and manage their own agents and automation capabilities,” Hartman said in an interview when the company first described the new service to Fierce Healthcare.
Hartman said future releases will build on this foundation with additional logic sets and features that support more out-of-the-box automation behavior, such as planned agent functionality built on the same clinically controlled structure.
Medication management and prescription processes are ripe for AI technology to automate manual tasks, provide faster support, and improve efficiency.
Industry forecasts estimate that agent AI in healthcare could grow 40% to 45% annually and exceed $5 billion in five years. However, according to Wolters Kluwer Health, effective AI must be based on rigorously validated drug and clinical content that is accessible within clinical workflows. MCP serves as a standardized integration layer between AI agents and external tools, making it essential for connecting AI agents and automation tools to evidence-based content. MCPs act as “a combination of universal translator and traffic controller,” Wolters Kluwer Health executives said in a blog post.
Currently, existing integration standards for drug information, such as application programming interfaces and flat files, are not optimized for agent AI workflows and can slow down AI-driven innovation. Wolters Kluwer Health claims that Medi-Span’s MCP server connects expert-curated drug content into a fast, dynamic format of workflows that is ready for use by AI agents.
“With the increasing use of AI systems in medication workflows, accuracy and consistency are essential given the impact these systems have on large-scale medication decisions,” Hartman said. “Medi-Span Expert AI aims to address key limitations of general-purpose large-scale language models by providing an evidence-based drug intelligence layer designed to support safe and reliable AI-driven decision-making.”
In general, Medi-Span Expert AI is designed for digital health technology companies, health IT vendors, and organizations that are building AI-driven workflows, Hartman said.
Hartman said early applications could include AI-enabled drug search and matching, drug interaction and duplication treatment screening, drug order validation, and retrieval of patient-specific drug information. Other potential uses include prescription and benefits management, pricing and contracts, and inventory and supply chain optimization.
“These capabilities give AI agents access to trusted, evidence-based Medi-Span drug intelligence. We do this through structured, machine-readable interfaces such as MCP, with the goal of automating safer and more reliable dosing decisions,” he said.
Hartman said the first group of developers with access to MCP will consist of “innovation partners and early adopters” who are actively building agent and AI-driven medication workflows.
“These developers are working on use cases where safe and definitive medication intelligence is critical, such as medication management, clinical decision support, pharmacy automation, and patient engagement,” he said.
Wolters Kluwer is making significant investments in AI to power its clinical decision support tools. In October, the company announced UpToDate Expert AI, a generative AI-powered version of a clinical decision support solution that has been widely used in the market for 30 years.
“Wolters Kluwer understands both the technology and patient care aspects of healthcare. Working with Wolters Kluwer will give us access to evidence-based content backed by over 30 years of knowledge and experience, combined with a robust AI architecture,” said Jean-Claude Saghbini, chief technology officer and president of health tech company Lumeris.
Editor’s note: This article has been updated to accurately reflect comments and quotes from Christian Hartman, Vice President of Product Innovation, Pharmacy and Medical Technology Solutions at Wolters Kluwer Health.
