Guardrail MCP
MCP serverAI & modelsDeterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use Guardrail MCP to get guardrail capabilities
From the project's README
As published by kadopi/guardrail-mcp in README.md.
Small, free, read-only Remote MCP for deterministic action preflight.
It exposes two tools:
get_guardrail_capabilitiesassess_action_risk
The check detects a deliberately small set of high-risk patterns: credential exposure, fund movement, external writes, and instruction overrides. It does not execute an action, persist a request, authenticate a user, charge a payment, call AI, or fetch external URLs.
Local use
npm run check
npm test
npm run dev
Endpoints: GET /, GET /health, and stateless Streamable HTTP POST /mcp.
Boundary
This is an informational deterministic preflight, not a safety guarantee or legal, financial, or security advice. Deployment and any public endpoint require separate approval.
Tools it offers (2)
What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.
get_guardrail_capabilitiesassess_action_risk
Signals
- Last commit
- Sep 2026
Advanced
- Delivery
- guardrail-mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
- Catalog kind
- mcp-server
- Gateway key
io-github-kadopi-guardrail-mcp- Source
- github.com/kadopi/guardrail-mcp
- Hosted endpoint
https://guardrail-mcp.kadopi.workers.dev/mcp