How to Use the Metatext MCP in Cursor

Q: How do I add the Metatext MCP Server to my Cursor workspace?

Create a .cursor/mcp.json file in your project root and paste the server configuration with your credentials. Turn on Agent mode in your Cursor chat panel to give the AI editor access to the NLP tools.

Q: Does the Metatext MCP Server integration support multiple active deployments in Cursor?

Yes, Cursor queries your account using listmodeldeployments to let you choose which endpoint to test. You can switch between staging and production models directly from the chat.

Q: How do I verify my account status from the editor?

You can ask the agent to run getaccountinfo to check your current usage and subscription limits. It prints your account metadata straight into the chat console.

Run NLP model predictions and manage datasets inside Cursor with this dedicated 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 Cursor

Create your Vinkius account to connect Metatext to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code using live predictions in Cursor

The `run_model_inference` tool lets Cursor run live predictions to test your application code with real model outputs instead of static mocks. When you write code in Agent mode, the editor executes the model to see exactly how it processes your inputs. This gives you immediate feedback on whether your parsing logic handles the model's actual response format. You spend less time guessing the JSON structure and more time writing the surrounding business logic.

Manage training data with your Cursor MCP Server

The `create_dataset_record` and `list_dataset_records` tools let your Cursor agent modify your training sets directly from your workspace. When you find edge cases in your local logs, you can tell the editor to push those exact payloads to your Metatext dataset. The agent handles the API calls in the background, updating your training data without you needing to export files or run curl commands. It makes iterating on model training data feel like a natural extension of your coding flow.

Query model metadata directly from the editor

The `get_model_details` and `list_nlp_models` tools allow Cursor to fetch details about your active models while you write integration code. Your agent reads the exact input and output schemas of your trained models to generate type-safe interfaces automatically. If you forget which model version is currently deployed, the agent queries your deployments to verify the active ID. This prevents hardcoding outdated model endpoints into your production environment.

Setup guide

Set up Metatext MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Metatext MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Metatext transactions." If the MCP tools are loaded correctly, Cursor will call the Metatext tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create a `.cursor/mcp.json` file in your project root and paste the server configuration with your credentials. Turn on Agent mode in your Cursor chat panel to give the AI editor access to the NLP tools.

Yes, the agent can read local files in your workspace, parse them, and use `create_dataset_record` to upload them to your training sets. It automates the tedious task of gathering training examples from your code base.

Yes, Cursor queries your account using `list_model_deployments` to let you choose which endpoint to test. You can switch between staging and production models directly from the chat.

You can ask the agent to run `get_account_info` to check your current usage and subscription limits. It prints your account metadata straight into the chat console.

Your dataset records and inference payloads are transmitted directly through the secure Vinkius proxy to the Metatext API. No data is cached or logged on Vinkius servers, ensuring your proprietary training examples and user inputs remain private.

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