How to Use the Metatext MCP in Claude

Q: How do I configure Metatext with my Claude Desktop app?

Open your claudedesktopconfig.json file and add the Metatext server to your mcpServers list with your API token. Once you restart the app, the hammer icon in the chat input will show all ten NLP tools ready for use.

Q: How does Claude Desktop know which Metatext model deployment to target?

The agent automatically runs listmodeldeployments to see what is currently active on your account. It then uses the returned deployment IDs to route your inference requests correctly.

Q: Do I need to write custom code to import datasets?

No, you don't need any code. Your agent uses createdatasetrecord to write new records directly to your datasets based on the text files or conversations you share in chat.

Run NLP model predictions and manage training datasets directly from your Claude Desktop chat window via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metatext MCP to Claude Desktop

Create your Vinkius account to connect Metatext to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Metatext with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run predictions inside Claude Desktop

The `run_model_inference` tool lets your agent trigger NLP predictions on your active deployments right inside the chat. You don't have to copy-paste payloads into terminal scripts or open external dashboards to test how your model responds to new prompts. Claude Desktop calls your active deployments using `list_model_deployments` to find the right endpoint, then sends the text payload directly. You see the classification or extraction results immediately in your conversation, making it easy to debug model behavior on the fly.

Explore datasets with your Claude Desktop MCP Server

The `list_nlp_datasets` and `get_dataset_details` tools give your Claude Desktop client direct visibility into your training data repositories. This MCP Server lets your agent inspect the structure of your data without requiring you to write custom SQL or Python scripts. You can ask the agent to fetch specific entries using `list_dataset_records` to verify formatting issues. When you find an error, the agent can append corrected examples to the source dataset using `create_dataset_record` to clean up your training pipeline.

Search and inspect models on the fly

The `search_nlp_models` and `list_nlp_models` tools allow Claude Desktop to find and analyze your catalog of trained models. Your agent compares accuracy metrics and training parameters by retrieving detailed metadata with `get_model_details`. This means you can ask which model is best suited for a task, and your agent will query your account, pull the stats, and present a clear comparison. You skip the manual search through the Metatext web UI entirely.

Setup guide

Set up Metatext MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Metatext MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Metatext MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under metatext-mcp.

json

{
  "mcpServers": {
    "metatext-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Metatext. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Metatext now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Metatext MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the Metatext server to your `mcpServers` list with your API token. Once you restart the app, the hammer icon in the chat input will show all ten NLP tools ready for use.

Yes, you can hook it up to claude.ai by going to Settings, opening the Integrations tab, and pasting your remote server URL. This lets you run predictions and manage datasets from any browser session without a local installation.

The agent automatically runs `list_model_deployments` to see what is currently active on your account. It then uses the returned deployment IDs to route your inference requests correctly.

No, you don't need any code. Your agent uses `create_dataset_record` to write new records directly to your datasets based on the text files or conversations you share in chat.

All data stays within the secure Vinkius V8 sandbox, meaning your raw dataset records and model input text are never exposed to external networks. Your API keys are encrypted at rest, and the server only talks to the official Metatext endpoint over HTTPS.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript