How to Use the Metatext MCP in VS Code Copilot

Q: How do I share the Metatext MCP Server configuration with my engineering team in VS Code Copilot?

Save the server configuration inside your repository at .vscode/mcp.json and commit it to Git. Anyone on your team using VS Code 1.96 or higher with Copilot will automatically have access to the tools.

Q: Can VS Code Copilot modify my Metatext datasets?

Yes, developers can use createdatasetrecord through the chat interface to add test cases to your datasets. This is perfect for logging edge cases discovered during local debugging sessions.

Q: How can I search for a specific model inside the chat?

Use the searchnlpmodels tool by asking Copilot to find models matching your target name. It returns the matching model IDs and their deployment status immediately.

Share NLP model access and dataset management across your entire team in VS Code Copilot with 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 VS Code Copilot

Create your Vinkius account to connect Metatext to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run team-wide predictions in VS Code Copilot

The `run_model_inference` tool lets your development team execute predictions directly from the VS Code Copilot chat panel. By committing an MCP Server configuration to your repository, every developer gets immediate access to test production models. This removes the friction of managing local environment variables or sharing API keys across the team. Developers can test how model updates affect code behavior without leaving their main workspace.

Inspect dataset schemas during code reviews

The `get_dataset_details` and `list_nlp_datasets` tools allow VS Code Copilot to fetch schema definitions and dataset metadata during development. This lets developers verify that their database models align perfectly with the expected training data formats. Instead of searching through web portals, you ask the agent to inspect the active dataset structures. It pulls the exact record layouts, helping you catch structural bugs before you commit your code.

Track active deployments inside your editor

The `list_model_deployments` and `search_nlp_models` tools provide real-time tracking of which models are running in your environments. Your agent queries your deployment status to ensure your application points to the correct active endpoints. If a model is redeployed, VS Code Copilot catches the update and can recommend code changes to match the new deployment details. It keeps your codebase in sync with your live NLP infrastructure.

Setup guide

Set up Metatext MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Metatext MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Metatext tools listed. Try asking: "List my recent Metatext transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Save the server configuration inside your repository at `.vscode/mcp.json` and commit it to Git. Anyone on your team using VS Code 1.96 or higher with Copilot will automatically have access to the tools.

Yes, developers can use `create_dataset_record` through the chat interface to add test cases to your datasets. This is perfect for logging edge cases discovered during local debugging sessions.

Vinkius manages authentication centrally, meaning your team uses a single secure endpoint token. You don't need to distribute sensitive Metatext master keys to every developer's local machine.

Use the `search_nlp_models` tool by asking Copilot to find models matching your target name. It returns the matching model IDs and their deployment status immediately.

All network traffic involving your dataset records and inference payloads is encrypted using TLS 1.3. The V8 isolate sandbox ensures that your data is handled in an ephemeral, zero-trust environment that never writes your inputs to persistent storage.

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