Life Sciences Leaders: Get to Know AI’s Model Context Protocol

Should technical AI standards be influencing the direction of your corporate strategy?  Before you say “no”, consider the case of MCP. 

When the history books look back on 2025, there will likely be a chapter about how the Model Context Protocol (MCP) transformed the way businesses interact with artificial intelligence.  While AI aficionados have been digging into how this emerging AI technology works, many C-suite executives remain totally unaware of it.  And that’s a shame, because this one standard represents a huge opportunity for every life sciences business. Here’s why. 

The MCP Paradigm Shift 

The Model Context Protocol is not just another technical standard – it represents a fundamental shift in how AI systems access, interpret, and act upon your organization’s most valuable data assets. Introduced by Anthropic in late 2024 and rapidly gaining adoption across the AI landscape, MCP is best understood as a universal connector that enables AI systems to securely integrate with your organization’s data repositories, internal tools, and external services. 

What makes MCP revolutionary is that it provides a standardized way for any AI system to connect with nearly any data source, replacing the complex maze of one-off integrations that have plagued previous attempts at building data-driven enterprises. As Anthropic describes it, MCP is “like a USB-C port for AI applications.” 

Very Rapid Traction 

While MCP is still in its early adoption phase in life sciences, organizations in other industries are already demonstrating its potential. Examples include: 

1. Block has implemented the protocol to enable AI agents that securely interact with their regulated financial systems. MCP allows their AI agents to securely access data and systems while maintaining rigorous security protocols for sensitive financial records.
2. DataCamp offers an MCP tutorial showcasing how MCP can be used to retrieve content changes, analyze those changes, and post the analysis into a workflow for processing.  This type of integration parallels how life sciences companies might deal with complex, evolving regulatory requirements. 
3. Several organizations using Notion’s knowledge management platform have built MCP servers that demonstrate how AI systems can securely query organizational knowledge bases without compromising data security. These implementations enable AI assistants to search and retrieve information from corporate knowledge repositories, create new documentation, and update existing resources—all through standardized interfaces. 

In less than a year, hundreds of MCP servers have been published, including interfaces to a wide variety of databases, file systems, PayPal, Box, web browsers, email services, Google, LLMs (OpenAI, Perplexity, Anthropic), Slack, Amazon, Spotify, Apple Notes, Stripe, and countless other systems and environments. 

The Value in Life Sciences Strategies 

So why should this technical strategy be a consideration in developing life sciences business strategies and roadmaps?  Here are three reasons: 

1. Enhanced Literature Review and Knowledge Synthesis.  Are your researchers manually sifting through published literature, patents, and internal documentation? With MCP, AI systems can do that faster and better.  To answer complex questions (e.g., “What are the latest findings on KRAS inhibitors for non-small cell lung cancer, and how do they compare with our current pipeline candidates?”), the MCP framework enables the AI to query PubMed, access internal research documents, examine competitive intelligence, and compare findings with proprietary compound databases. 
2. Laboratory Informatics.  From a data access and management perspective, laboratory systems and device instrumentation can be quite challenging to manage.  MCPs offer a mechanism for developing simple ways of accessing and leveraging that information without investing in highly complex manual programming tasks. 
3. Accelerating Clinical Trial Design and Analysis.  Clinical trials represent one of the most time-consuming and expensive aspects of drug development. MCP can help streamline this process by enabling AI systems to analyze historical trial data to identify optimal patient selection criteria; simulate various trial designs; monitor ongoing trials in real-time, flagging potential issues before they become problematic; and adapt protocols based on emerging data. 
4. Supply Chain Optimization and Manufacturing Intelligence. MCP allows AI models to connect with manufacturing execution systems, quality management systems, inventory / logistics platforms, and regulatory compliance databases to create comprehensive views of the supply chain (e.g., identifying bottlenecks, predicting potential disruptions, and recommending optimization strategies). 
5. Product Safety & Surveillance.  The heterogeneous nature of monitoring drug, vaccine, and device use around the world is daunting.  But MCP creates the opportunity for automations in signal detection, data aggregation, reporting, and management.  This capability becomes more important as new use cases for leveraging data from healthcare delivery solutions (e.g., electronic medical records, pharmacy systems) become more prominent. 
6. Regulatory Intelligence and Compliance.  By connecting to regulatory databases, internal documentation systems, and communication platforms, MCP-enabled AI models can maintain comprehensive awareness of evolving requirements while streamlining submission processes.  The integration can also help companies detect and stay ahead of evolving compliance requirements and audit trends. 
7. Healthcare Provider Engagement. Sales representatives and medical science liaisons can leverage MCP-enabled AI assistants that simultaneously access CRM systems containing relationship history, scientific databases with the latest research, internal product documentation, and compliance systems to ensure appropriate engagement. 
8. Patient Support and Adherence Programs.  For patient-facing teams, MCP enables the creation of highly personalized support systems that draw from multiple data sources to address individual needs while respecting privacy requirements. 

1. Assess the potential business impact of MCP-enabled AI across your value chain – what capabilities are most important for your growth goals? 
2. Identify high-value pilot opportunities that align with strategic priorities – where can you get the biggest lift? 
3. Validate that your data infrastructure can support reliable MCP implementations – do you have a solid data strategy and architecture that can underpin your growth goals? 
4. Establish clear security and governance frameworks – is it clear what data sources can be connected to AI systems and who can access them? 
5. Consider a fractional Chief AI Officer to help drive the assessment, planning, and execution – would interim leadership and expertise amplify the benefits you receive? 

The most successful life sciences organizations will be those that view MCP not merely as a technical standard but as a strategic enabler that fundamentally changes how intelligence – both human and artificial – can be applied to create value throughout the enterprise. The convergence of AI with domain-specific expertise will likely drive the next wave of innovation in life sciences, and MCP may well be the connective tissue that makes it possible. What MCP implementation opportunities do you see in your organization? 

CREO provides a comprehensive set of life sciences AI services that help organizations plan and adopt AI capabilities with MCP.  Contact us today to learn more.