An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Hallucination Detection Score to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get a mathematical score for your agent's reliability.

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

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Hallucination Detection Score.

  1. 01

    Analyze claim accuracy

    This capability evaluates how truthful an output is by checking it against consensus and verified data.

  2. 02

    Calculate consensus metrics

    Use this to compare specific claims against the outputs of other agents to find agreement levels.

  3. 03

    Extract fact claims

    This capability pulls individual assertions out of a block of text so you can audit them one by one.

Real work

What teams actually run

01

Automated Fact Checking

Run an audit on long-form AI reports to ensure every sentence is backed by data.

02

Multi-Agent Verification

Compare outputs from different agents to see if they reach the same conclusion.

03

Risk Management

Assign a risk level to AI outputs before they are presented to end users.

04

Data Integrity Audits

Isolate specific assertions in a dataset to verify their accuracy against a source of truth.

One connector, every AI

Hallucination Detection Score works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Hallucination Detection Score to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

834ms average. Fast in production.

Hallucination Detection Score is checked daily against the live service.

Daily averagePeak 916ms
Oct 3Today
Fastest day
700ms
Slowest day
916ms
14-day trend
Stable-4%

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 Detection Score, so you can see the experience inside your AI.

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

Hallucination Detection Score Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_f2BpVimTNFp2MgsaHMjEB7zPAEkEtZWc6x4y3856/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 Detection Score capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "hallucination-detection-score-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_f2BpVimTNFp2MgsaHMjEB7zPAEkEtZWc6x4y3856/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

Guided setup for Claude? Set up Hallucination Detection Score in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Hallucination Detection Score owners hand off.

This is for technical teams building or using AI agents that require high levels of factual accuracy.

  • 01

    AI Engineers

    They use this to audit the reliability of custom agent workflows.

  • 02

    Data Scientists

    They use this to quantify error rates in model outputs.

  • 03

    QA Testers

    They use this to automate the verification of AI generated content.

FAQ

Questions Hallucination Detection Score owners ask.

  • 01

    How does this MCP calculate hallucination scores?

    It uses a deterministic framework that compares agent outputs against a verified knowledge base and consensus from other agents.

  • 02

    Which AI clients can use this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I use this to check if multiple agents agree?

    Yes, you can use the calculate_consensus_metrics capability to compare claims against peer outputs.

  • 04

    Does this work with any AI model?

    This works with any AI client or agent that supports the Model Context Protocol.

  • 05

    How do I get a breakdown of individual facts?

    Use the extract_fact_claims capability to isolate specific assertions from a larger text block.

  • 06

    How is the hallucination probability calculated?

    The probability is a weighted metric: 50% for claims verified by the reference knowledge base, 30% for consensus with other agents, and 20% for claims with source attribution.

  • 07

    What is the difference between verified claims and consensus?

    Verified claims are checked against a provided ground truth (knowledge base), while consensus (cross-agent agreement) measures how much the output aligns with other agents' responses on the same topic.

  • 08

    Can I use this to check specific assertions?

    Yes, you can use the extract_fact_claims capability to break down a text block into individual, testable assertions for granular analysis.

Explore

More in AI Safety

Suggestions

Connect Hallucination Detection Score to Claude, Cursor, ChatGPT & more