# phi-redact-mcp

> phi-redact-mcp — rinava-phi-mcp. Use this tool when you need to protect sensitive patient information by redacting PII/PHI from text data before processing with large language models. It solves the problem of ensuring HIPAA compliance in AI workflows, providing a fail-closed and self-hosted solution for secure data handling. The tool takes in text input and outputs redacted text, making it ideal for use cases where sensitive health information is involved.

Canonical page: https://skillsregistry.net/skills/rinava-phi-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rinava-phi-mcp

## Description

An MCP server that redacts PII/PHI from text before it ever reaches an LLM — self-hosted, fail-closed, and HIPAA-aware.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qs6gn8d34r)
- **Repository:** <https://github.com/Rinava/umbryn-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rinava-phi-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rinava-phi-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rinava-phi-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt