Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Guardrail Violation Detector with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Analyzes AI agent outputs for safety and compliance violations.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 3 capabilities

The complete Guardrail Violation Detector capability set.

These are the exact actions your AI can choose when you ask it to work with Guardrail Violation Detector.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Guardrail Violation Detector.

  1. 01

    Get guardrail configuration

    Retrieves the current active rules and their definitions

  2. 02

    Analyze output violations

    Performs a full audit of an agent response against a set of rules

  3. 03

    Get historical false positive rate

    Retrieves the accuracy metric for a specific guardrail rule

Observed, not estimated

838ms average. Fast in production.

Guardrail Violation Detector is checked daily against the live service.

Daily averagePeak 952ms
Aug 20Today
Fastest day
689ms
Slowest day
952ms
14-day trend
Slowing+13%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Guardrail Violation Detector, so you can see the experience inside your AI.

It does not authenticate your account with Guardrail Violation Detector. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Guardrail Violation Detector Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_YNYgljFnARbyHucIWxHCvPzZQiRfCobNSYrS0ASd/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Guardrail Violation Detector capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "guardrail-violation-detector-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YNYgljFnARbyHucIWxHCvPzZQiRfCobNSYrS0ASd/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Guardrail Violation Detector owners ask.

  • 01

    How is the violation severity determined?

    Severity is based on the composite score: Info for scores below 0.2, Warning for 0.2 to 0.5, and Block for scores above 0.5. Additionally, any single rule exceeding 0.8 triggers a Block.

  • 02

    Can I see which rules are currently active?

    Yes, you can use the get_guardrail_configuration capability to retrieve the current list of active rules and their thresholds.

  • 03

    What happens if both PII and toxicity are detected?

    The system is designed to handle cascading violations; if both PII and toxicity are detected in the same output, the severity level is automatically escalated.

Explore

More in Quality Assurance

Suggestions