An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Metatext 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. Control your machine learning pipelines through natural conversation.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Metatext.

  1. 01

    Get dataset details

    This capability retrieves specific metadata for a dataset. Use it to inspect the structure or properties of your data collections.

  2. 02

    List nlp datasets

    This capability provides a list of all your datasets. Use it to navigate your stored data collections.

  3. 03

    List model deployments

    This capability shows you all your active model deployments. It helps you keep track of what is currently live and running.

  4. 04

    List dataset records

    This capability retrieves the individual entries within a dataset. Use it to audit or review your training data.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Metatext.

  1. 05

    Run model inference

    This capability executes a prediction using one of your deployed models. It is how you get real-time results from your NLP logic.

  2. 06

    Search nlp models

    This capability finds specific models by their name. It is the fastest way to locate a particular model in a large library.

  3. 07

    Create dataset record

    This capability adds a new entry to your specified dataset. Use it to feed new training or evaluation data into your pipelines.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Metatext.

  1. 08

    Get model details

    This capability fetches information about a specific NLP model. It provides the necessary context for understanding model capabilities.

  2. 09

    List nlp models

    This capability returns a list of all your trained NLP models. Use it to see what you have available for inference.

  3. 10

    Get account info

    This capability pulls your Metatext account details. It is useful for checking your current subscription or account status.

Real work

What teams actually run

01

Rapid Prototyping

Test how a new model performs on specific text samples without writing a single line of Python.

02

Data Labeling Oversight

Quickly add new labeled examples to a dataset to refine model training.

03

Model Monitoring

Check the status of your active deployments to ensure your NLP services are running.

04

Dataset Auditing

List and inspect records in a dataset to verify the quality of your training data.

Automate a task

Put Metatext 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

Metatext 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 Metatext 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

896ms average. Fast in production.

Metatext is checked daily against the live service.

Daily averagePeak 1149ms
Oct 3Today
Fastest day
742ms
Slowest day
1149ms
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. 10 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 Metatext, so you can see the experience inside your AI.

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

Metatext Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_77VAYStySeROKtVdW5OxQRJpWkfEWaDXQ23SvhBu/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 — Metatext capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "metatext-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_77VAYStySeROKtVdW5OxQRJpWkfEWaDXQ23SvhBu/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 Metatext in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Metatext owners hand off.

This MCP is built for technical users who manage machine learning workflows and want to interact with them via natural language.

  • 01

    ML Engineers

    They use the agent to trigger inference and check model deployment status.

  • 02

    Data Scientists

    They manage datasets and add new records for training directly through chat.

  • 03

    NLP Developers

    They orchestrate model workflows and search for specific models to use in applications.

FAQ

Questions Metatext owners ask.

  • 01

    How do I connect my Metatext account?

    You subscribe to the MCP on Vinkius and then enter your Metatext API Key to establish the connection.

  • 02

    Which AI clients can I use with this MCP?

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

  • 03

    Can I run predictions on my models?

    Yes, you can use the run_model_inference capability to get predictions from your deployed models.

  • 04

    Do I need to write code to manage my datasets?

    No, you can manage datasets, add records, and list entries using natural language commands through your agent.

  • 05

    Can I see which models are currently live?

    Yes, the list_model_deployments capability allows you to see all your active deployments.

  • 06

    How do I find my Metatext API Key?

    Log in to Metatext and navigate to your account settings to find and copy your API Key.

  • 07

    Can I run inference on any model type?

    Yes, as long as the model is fully trained and deployed, you can use the run_model_inference capability.

  • 08

    Is my AI data secure?

    Absolutely. Your token is encrypted at rest and injected securely at runtime.

Explore

More in Developer Tools

Suggestions

Connect Metatext to Claude, Cursor, ChatGPT & more