MCPLow riskUnclaimed

healthclaw-guardrails

Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation

aks129aks129/healthclaw-guardrails★ 30Updated Jul 4, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.aks129/healthclaw-guardrails",
  "description": "Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation",
  "repository": {
    "url": "https://github.com/aks129/HealthClawGuardrails",
    "source": "github"
  },
  "version": "1.6.0",
  "websiteUrl": "https://healthclaw.io",
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://mcp-server-production-5112.up.railway.app/mcp",
      "headers": [
        {
          "description": "Tenant identifier — the public demo tenant 'desktop-demo' works without credentials",
          "name": "X-Tenant-Id"
        },
        {
          "description": "Tenant-bound HMAC step-up token, required for write-tier tools and non-public tenant reads",
          "isSecret": true,
          "name": "X-Step-Up-Token"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Networkmcp-server-production-5112.up.railway.appmcp-server-production-5112.up.railway.app
Needs credentialsX-Step-Up-TokenX-Step-Up-Token
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #11.6.0latestOct 7, 2026