phi-guard-mcp

Purpose: Preventing exposure of protected health information (PHI) when sending medical text to AI agents.

Inferred · not functionally tested

Audience: healthcare developers and data privacy engineers

Inferred · not functionally tested

Functions: data_extraction

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, api_only, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

phi-guard-mcp is an AI & LLM security project. Inferred · not functionally tested: It focuses on preventing exposure of protected health information (PHI) when sending medical text to AI agents. Inferred · not functionally tested: It is built as an open-source project for healthcare developers and data privacy engineers. Basis unknown · not verified: phi-guard-mcp is open source under the MIT license. Basis unknown · not verified: phi-guard-mcp is available on the command line and API, and it can be self-hosted.

Behind phi-guard-mcp is charlesree826, and it first shipped in 2026. The project is developed in the open on GitHub with 8 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are PHI detection, PHI redaction, and audit logging. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.

Summary written by a language model from the project’s public pages.