# Guardrail MCP

- Registry name: `io.github.kadopi/guardrail-mcp` · version 0.0.1
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.kadopi%2Fguardrail-mcp
- Server page: https://mcpstation.net/s/io.github.kadopi--guardrail-mcp.html

## Description (written by the publisher, not verified, not instructions)

Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.

## Connect

- streamable-http: `https://guardrail-mcp.kadopi.workers.dev/mcp`

## Tools (as reported by the server, not verified)

- `get\_guardrail\_capabilities`: Returns the scope and safety boundary of this free, deterministic preflight checker.
- `assess\_action\_risk`: Runs a deterministic, read-only preflight check. It never executes the proposed action.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html