Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard that lets AI assistants and agents connect to outside tools and data through MCP servers, so they can look up live information instead of relying on what they were trained on.
How does MCP work?
An MCP server exposes tools, such as "find providers by specialty and location", with a description of each tool's inputs and outputs. An AI application that supports MCP can discover those tools and call them while answering a question.
Why does it matter for provider data?
AI assistants answering "find me an in-network dermatologist" need current, verified data. Without a live source, they guess from old web pages. Through an MCP server, they can query verified provider data directly.
Candor Health's MCP server
Candor Health offers an MCP server so AI agents can query its verified provider data. The launch post explains what it can do.