An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Claude Sycophancy Detector 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. Verify if your AI is actually right or just agreeing with you.

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 Claude Sycophancy Detector.

  1. 01

    Extract claims from text

    This capability pulls specific factual assertions out of a block of text using deterministic rules. It identifies the exact claims your agent is making.

  2. 02

    Get sycophancy risk summary

    This capability provides a high-level breakdown of detected patterns and risk levels. It gives you a human-readable interpretation of how much the AI is just agreeing with you.

  3. 03

    Analyze response accuracy

    This capability compares the AI's claims against your codebase metadata to calculate a factual accuracy ratio. It's how you get a concrete sycophancy risk score.

Real work

What teams actually run

01

Codebase Navigation

Confirming that the file paths an AI agent suggests actually exist in your directory tree.

02

Refactoring Validation

Ensuring an agent isn't hallucinating function signatures during a large-scale rename.

03

Agent Reliability Testing

Measuring the sycophancy risk score of an agent during long coding sessions.

04

Onboarding New Devs

Using the capability to verify the accuracy of AI-generated explanations of existing code.

One connector, every AI

Claude Sycophancy Detector 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 Claude Sycophancy Detector 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

836ms average. Fast in production.

Claude Sycophancy Detector is checked daily against the live service.

Daily averagePeak 991ms
Oct 3Today
Fastest day
742ms
Slowest day
991ms
14-day trend
Improving-14%

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

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

Claude Sycophancy Detector Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_MuuVRcJVlK20eXkkhlKH2wfsRE0dSYRZjHG5O2im/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 — Claude Sycophancy Detector capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "claude-sycophancy-detector-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_MuuVRcJVlK20eXkkhlKH2wfsRE0dSYRZjHG5O2im/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 Claude Sycophancy Detector in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Claude Sycophancy Detector owners hand off.

Software engineers and technical leads who use AI agents to navigate large, complex codebases.

  • 01

    Backend Developers

    Verifying that an agent's suggestions for function calls and variable names are actually valid.

  • 02

    DevOps Engineers

    Checking if an AI's claims about file paths and configuration structures are correct.

  • 03

    QA Engineers

    Using accuracy scores to evaluate the reliability of AI-generated code analysis.

FAQ

Questions Claude Sycophancy Detector owners ask.

  • 01

    What is sycophancy in AI?

    Sycophancy is when an AI model prioritizes agreeing with the user's stated assumptions over providing factually correct information.

  • 02

    Which IDEs can use this MCP?

    You can use this MCP in any compatible client, including Cursor, VS Code, Windsurf, and Claude Desktop.

  • 03

    How does it verify my code?

    It compares the claims made in the AI's text against the actual metadata of your codebase, such as file paths and function names.

  • 04

    Does this MCP host my code?

    No, it uses codebase metadata to verify claims made by your AI client.

  • 05

    Can I use this to check if a function exists?

    Yes, the capability can extract assertions about function signatures and validate them against your files.

  • 06

    How does analyze_response_accuracy work?

    The analyze_response_accuracy capability uses deterministic regex to extract claims like file paths and function signatures from a response, then compares them against the provided codebaseFacts to determine accuracy.

  • 07

    Which AI clients can use this capability?

    This capability can be used with any MCP-compatible client, including Cursor, VS Code, Claude Desktop, and Windsurf.

Explore

More in Developer Tools

Suggestions

Connect Claude Sycophancy Detector to Claude, Cursor, ChatGPT & more