Guardrail MCP

io.github.kadopiPublished by GitHub account kadopiv0.0.1Updated Oct 27, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A free, read-only remote MCP server that runs deterministic preflight checks on proposed actions for credential, payment, write and prompt-override risks.

What you can do
  • Describe the checker's scope and safety boundary
  • Run a deterministic, read-only risk assessment on a proposed action, flagging credential exposure, fund movement, external writes and instruction overrides
  • Report the result without executing the action, storing the request or calling external services
When to use it
Useful when an assistant is about to propose a sensitive step — handling credentials, moving money, writing to external systems or following embedded instructions — and you want a quick, consistent second opinion before acting. It is informational only, not a safety guarantee.
Requirements
Remote Streamable HTTP endpoint; no authentication, environment variables or headers are declared. Nothing needs to be installed locally.
Before you install
The check covers only a deliberately small set of high-risk patterns and is explicitly not a safety guarantee or legal, financial or security advice. It does not authenticate users, so do not treat a passing result as authorization; the README notes that deployment and any public endpoint require separate approval.

Installation

In SourceWeft

  1. Open Guardrail MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.kadopi%2Fguardrail-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "guardrail": {
      "type": "http",
      "url": "https://guardrail-mcp.kadopi.workers.dev/mcp"
    }
  }
}

README

Guardrail MCP

Small, free, read-only Remote MCP for deterministic action preflight.

It exposes two tools:

  • get_guardrail_capabilities
  • assess_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

bash
npm run checknpm testnpm 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.

Source: README.md at commit 5929454

Tools

2

get_guardrail_capabilities

Get Guardrail MCP capabilities

Returns the scope and safety boundary of this free, deterministic preflight checker.

Takes no parameters.

assess_action_risk

Assess action risk

Runs a deterministic, read-only preflight check. It never executes the proposed action.

Parametersactionrequiredcontent

Version history

1
  1. v0.0.1LatestSep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.