# What Is an MCP Connector for Health Records?

The Model Context Protocol (MCP) is a standard way for AI applications to connect to outside data and tools. A health records connector, like Flexpa's at https://api.flexpa.com/mcp/consent, lets your assistant read records you've authorized: you sign in through Flexpa, and the assistant can then use tools such as get_health_summary or get_claims to answer your questions.

How it works: Flexpa Consent -> Patient access token -> Records tools. The patient records MCP connector requires patient authorization.

## What it can and can't do

- Patient records tools require a patient access token obtained through Flexpa Consent.
- Available records depend on the sources connected through that authorization.
- You can revoke Flexpa access; review the assistant provider's data policies before sharing.

## Where it works

Flexpa documents setup for supported MCP clients in its Health records for agents guide. Client features and account requirements can change.

## Questions

**What is an MCP connector?** An MCP connector uses the Model Context Protocol to connect an AI application to outside data or tools. Flexpa's patient records connector requires authorization through Flexpa Consent.

**What access does the Flexpa health records connector require?** Flexpa's patient records MCP connector requires a patient access token from Flexpa Consent. Review the records you authorize and the AI provider's data policies before sharing. You can revoke Flexpa access.

## More

- [Connect your records to Claude or ChatGPT](https://www.flexpa.com/connect-health-records-to-ai)
- [Health records for agents (docs)](https://www.flexpa.com/docs/guides/agents)
- [Health tools for agents](https://www.flexpa.com/agents)

Last updated 2026-11-11.