mcpField
G
Guardrail MCP

Guardrail MCP

Remote
github.com/kadopiSecurity0Updated 8w ago
Repository

About Guardrail MCP

Guardrail MCP is a small, read-only remote service for deterministic preflight checks. It flags selected risks in proposed actions without executing them, storing requests, or calling AI.

Key features

  1. 01Credential exposure detection
  2. 02Fund movement detection
  3. 03External write detection
  4. 04Instruction override detection
  5. 05Deterministic risk assessment

Use cases

  1. 01Checking an action before exposing credentials
  2. 02Reviewing a proposed funds transfer
  3. 03Preflighting an external write
  4. 04Flagging instruction overrides

MCP support

Exposes `get_guardrail_capabilities` and `assess_action_risk` through stateless Streamable HTTP at `/mcp`.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://guardrail-mcp.kadopi.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

2

This tool takes no parameters.

Details

From the project 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

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.