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

Use Hallucination Detector with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Detect factual contradictions across multiple LLM responses to identify potential hallucinations.

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 Hallucination Detector capability set.

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

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Hallucination Detector.

  1. 01

    Analyze consistency

    Evaluates a set of LLM responses to determine if they are factually consistent

  2. 02

    Extract claims

    Decomposes text into individual factual assertions

  3. 03

    Find contradictions

    Compares sets of claims to identify logical conflicts

Observed, not estimated

835ms average. Fast in production.

Hallucination Detector is checked daily against the live service.

Daily averagePeak 1028ms
Aug 20Today
Fastest day
680ms
Slowest day
1028ms
14-day trend
Stable-1%

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 Hallucination Detector, so you can see the experience inside your AI.

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

Hallucination Detector Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_hkgY7Z5J8UbQd7NqclEuQsXU1SpnqkJ6HHDo9KPz/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 — Hallucination Detector capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "hallucination-detector-via-consistency-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_hkgY7Z5J8UbQd7NqclEuQsXU1SpnqkJ6HHDo9KPz/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 Hallucination Detector owners ask.

  • 01

    How does the consistency score work?

    The score is calculated by subtracting the ratio of unique contradictions to the total number of extracted claims from 1.0. A score of 1.0 means perfect agreement.

  • 02

    What can I do with analyze_consistency?

    You can use analyze_consistency to pass a list of multiple LLM responses and receive a report containing a consistency score and indices of suspect responses.

  • 03

    Can I customize the strictness of the detection?

    Yes, you can provide a custom threshold value to analyze_consistency to define when a set of responses should be flagged as inconsistent.

Explore

More in Reliability

Suggestions