Enhancing Note Accuracy via Model Context Protocol (MCP)
R
Richard Bosworth
I wonder if integrating Model Context Protocol (MCP) could improve the accuracy of the clinical notes Heidi generates. If Heidi could securely access up-to-date guidelines and our local formularies, for example, the notes would be much more precise and reliable. Of course, I'm aware that allowing an AI to connect to external databases raises security concerns. Perhaps limiting MCP connections to approved secure servers, internal systems, or carefully vetted resources would be a way to manage this. Alternatively, would it be feasible to explore MCP calls that strictly do not involve patient-identifiable data?
Phil from Heidi
Hey Richard
Phil from the Product team @ Heidi here. Would love to understand more. I'll email you directly for a discussion if yo have time. If you don't - have a few questions:
- What specific clinical information do you find yourself manually looking up most frequently during or after documentation?
- Would this integration be most valuable during live documentation, or when Heidi is helping you complete follow-up tasks after the encounter?
- Which systems would provide the most value - internal formularies/protocols, or external clinical guidelines?