An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Ragas to ChatGPT, Claude and Gemini

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. Measure and improve your agent's performance without leaving your IDE.

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 · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Ragas.

  1. 01

    List experiments

    This capability shows you all the experiments tied to a specific dataset.

  2. 02

    Get experiment

    Use this to pull detailed data for a single experiment.

  3. 03

    Run evaluation

    This triggers a new evaluation run for a dataset to calculate scores like faithfulness and answer relevancy.

  4. 04

    List metrics

    This provides a list of all the evaluation metrics available to use.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Ragas.

  1. 05

    Get results

    This retrieves the final results once an experiment is finished.

  2. 06

    List datasets

    This capability lists all the evaluation datasets you have available.

  3. 07

    Get dataset

    Use this to get specific details about an evaluation dataset.

Real work

What teams actually run

01

Iterative RAG Tuning

Compare how changing your retrieval settings affects faithfulness scores immediately.

02

Hallucination Monitoring

Run evaluations to ensure your agent stays grounded in the provided context.

03

Dataset Organization

Manage and list your evaluation datasets through your AI client.

04

Experiment Tracking

Keep a record of how different model versions perform on the same data.

Automate a task

Put Ragas to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Ragas 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 Ragas 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

879ms average. Fast in production.

Ragas is checked daily against the live service.

Daily averagePeak 1115ms
Oct 3Today
Fastest day
698ms
Slowest day
1115ms
14-day trend
Slowing+43%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 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 Ragas, so you can see the experience inside your AI.

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

Ragas Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_mQUV7klN4rh09rRcp9ld3cwceCP25oL5Lk8res4B/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 — Ragas capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ragas-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mQUV7klN4rh09rRcp9ld3cwceCP25oL5Lk8res4B/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 Ragas in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Ragas owners hand off.

This MCP is built for technical teams building and refining RAG-based applications.

  • 01

    AI and ML Engineers

    They use it to run pipeline evaluations without writing manual Python scripts.

  • 02

    LLM QA Specialists

    They use it to check datasets and benchmark results to keep hallucination rates low.

  • 03

    Data Scientists

    They use it to compare RAG configurations side-by-side using unified metrics.

FAQ

Questions Ragas owners ask.

  • 01

    How do I use Ragas with my AI client?

    You connect the MCP by providing your Ragas Application URL and Application Token. Once connected, you can simply ask your agent to run evaluations or fetch metrics.

  • 02

    What metrics can this MCP provide?

    The MCP can access Ragas metrics such as faithfulness and answer relevancy to score your RAG pipelines.

  • 03

    Do I need to write Python code to run evaluations?

    No. This MCP allows your agent to trigger evaluations and manage datasets through natural language commands instead of manual scripting.

  • 04

    Can I manage my existing Ragas datasets?

    Yes. The MCP includes capabilities to list, get details for, and organize your existing datasets.

  • 05

    Can I compare different versions of my agent?

    Yes. You can use the capability to track and compare metrics across different experiments and agent versions.

  • 06

    How do I secure an App Token for Ragas?

    Log into your provided Ragas dashboard. In your project's settings or dedicated security section, you will find the ability to generate a new Application Token. Copy it immediately, as it may only appear once.

  • 07

    What format is required to upload a dataset?

    The capability uses common array formats through the MCP wrapper. When passing data, the AI maps arrays containing question, ground_truth and contexts natively matching Ragas base requirements.

  • 08

    Does the server evaluate prompts automatically during testing?

    Yes. When triggering evaluations, Ragas uses its own sophisticated metrics (like Faithfulness, Answer Relevance) running internally. The MCP server simply pipes these generated reports back to your chat.

Explore

More in AI Frontier

Suggestions

Connect Ragas to Claude, Cursor, ChatGPT & more