healthclaw-guardrails

MCP serverAI & models

Your AI can work with healthcare data in the FHIR format while sensitive information stays protected. Once added, personal health information is redacted, every access is recorded in an audit trail, and sensitive steps require extra verification. Data from different tenants is kept isolated from each other.

Use healthclaw-guardrails in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add healthclaw-guardrails and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use healthclaw-guardrails

Needs your own Tenant ID account. Keys stay in your vault.

Details

Available today. Use it from your connected AI after setup.

Add healthclaw-guardrails to your AI, then connect it to the FHIR healthcare data you want your AI to work with. Check the audit trail to see exactly what your AI accessed.

healthclaw-guardrailsStart free

What your AI can do with it

Read and work with healthcare records stored in the FHIR format
Redact personal health information from records your AI handles
Record every access in an audit trail you can review
Require an extra verification step before sensitive actions
Keep each tenant's data isolated from other tenants

Install healthclaw-guardrails

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

Claude Code
claude mcp add --transport http --scope user healthclaw-guardrails 'https://mcp-server-production-5112.up.railway.app/mcp'
Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://mcp-server-production-5112.up.railway.app/mcp
Add a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=healthclaw-guardrails&config=eyJ1cmwiOiJodHRwczovL21jcC1zZXJ2ZXItcHJvZHVjdGlvbi01MTEyLnVwLnJhaWx3YXkuYXBwL21jcCJ9
Open the link and Cursor adds the server at that address.
ChatGPT
https://mcp-server-production-5112.up.railway.app/mcp
In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add healthclaw-guardrails --url 'https://mcp-server-production-5112.up.railway.app/mcp'
Run it once, then sign in with codex mcp login healthclaw-guardrails if the server asks for an account.

From the project's README

As published by aks129/healthclawguardrails in README.md. This repository publishes several servers, so only the opening is shown here.

The open-source security layer between AI agents and clinical data.

FHIR standardized how health data is structured. MCP standardized how AI connects to tools. Nobody standardized the guardrails in between. This project does.

▶ Watch the 90-second demo All records are synthetic. The chat ran on a third-party model, best of four takes. No clinician has signed off yet. How it was made.

Shortened here. Read the whole README on GitHub.

Signals

GitHub stars: 30
Forks: 13
Last commit: Oct 2026

Advanced

Delivery: healthclaw-guardrails MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type: mcp-server
Key: io-github-aks129-healthclaw-guardrails
Source: github.com/aks129/healthclawguardrails
Hosted endpoint: https://mcp-server-production-5112.up.railway.app/mcp

github.com/aks129/healthclawguardrails

More in AI & models

context7
MCP server · upstash
More in AI & models AdButler
MCP server · adbutler
More in AI & models atom-mcp-server
MCP server · a7om-ai
More in AI & models ottasia
MCP server · aiweather-anurag
More in AI & models unphurl
MCP server · 123ergo
More in AI & models microsoft-learn-mcp
MCP server · microsoftdocs
More in AI & models