Healthclaw Guardrails MCP Server

by aks129 Your server? Claim it

answering

Healthclaw Guardrails is answering right now. Last checked 11 min ago. Last commit 15 Sep 2026.

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

Uptime history 48 days of history · worst day 99%

48 days agonow

100.0%

Uptime 24h

91 of 91 checks

—

Tools

hidden behind auth

295 ms

Response time

average over 24h

Stars

last commit 15 Sep 2026

What the code does

We read the source, 1 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Executes code built at runtime r6/purge.py:73

            module = __import__(import_path, fromlist=[attr])

Builds a database query by concatenation r6/smbp/demo_history.py:270, careagents/templates/home.html:216

        am_s = int(153 - drop + bounce + plateau)

Runs an external command openclaw/bot.py:882, deploy/careagents/imessage_relay.py:96

            result = subprocess.run(

Sends data to a third-party sink r6/telegram_push.py:26, openclaw/bot.py:1155

_TELEGRAM_API = 'https://api.telegram.org'

Page executes code built at runtime templates/mcp_apps/wearables.html:172, templates/mcp_apps/care_gaps.html:164

      grid.innerHTML = providers.map(p =>

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add healthclaw-guardrails --transport http https://mcp-server-production-5112.up.railway.app/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "healthclaw-guardrails": {
      "url": "https://mcp-server-production-5112.up.railway.app/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.healthclaw-guardrails]
url = "https://mcp-server-production-5112.up.railway.app/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "healthclaw-guardrails": {
      "url": "https://mcp-server-production-5112.up.railway.app/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "healthclaw-guardrails": {
      "url": "https://mcp-server-production-5112.up.railway.app/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp-server-production-5112.up.railway.app/mcp	streamable-http	needs key	350 ms	11 min ago

Alternatives to Healthclaw Guardrails

same job, measured the same way

Delego

by delego-dev

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

202 installs/wk local only

MCP Gateway

by titus-civic

Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.

answering

Grantex

by mishrasanjeev

OAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.

97 installs/wk local only

Tenantguard

by rudrendupaul

Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.

99 installs/wk local only

Agentpay Sentinel MCP

by rumblingb

Security guardrails for AI agent payments

local only

Agent Audit MCP

by rumblingb

Immutable audit trail for agent-to-agent interactions

local only

QueryPilot

by nickklos10

Safe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals

39 installs/wk local only

Agent Guardrail MCP Server

by jarvisonm4

Action-level governance for AI agents -- control what they DO, not what they SAY

81 installs/wk local only

Healthclaw Guardrails — questions

Answers built from our own checks of this server.

Why is there no tool list for Healthclaw Guardrails?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is Healthclaw Guardrails working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 295 ms. The bar chart above shows every period we have measured.

How do I connect Healthclaw Guardrails?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key: it refuses anonymous clients.

Does Healthclaw Guardrails need an API key?

Yes. Every time we knock, Healthclaw Guardrails answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Healthclaw Guardrails?

It answers our handshake in 295 ms on average, which is faster than 51% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Healthclaw Guardrails open source?

Yes — it is published under the MIT licence, written in Python, 30 stars on GitHub and 85 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.