HealthClaw Guardrails
Verified IntegrationClient Configuration
— Connect HealthClaw Guardrails to Claude Desktop or Cursor in seconds{
"mcpServers": {
"healthclaw-guardrails": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-healthclaw-guardrails"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Establishes a robust security layer with PHI redaction, immutable audit trails, and step-up authorization between AI agents and FHIR clinical data.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for HealthClaw Guardrails
Yes, it functions as a vendor-neutral proxy, compatible with any AI agent (supporting MCP, Claude plugins, OpenAI/Gemini adapters) and any FHIR server (e.g., HAPI, Epic, Medplum), ensuring broad interoperability.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.