How to Use the Metatext MCP in OpenAI Agents SDK

Q: Can a Metatext model search be run dynamically in OpenAI Agents SDK?

Yes, the agent can call searchnlpmodels to locate specific models based on task requirements. It can then pull full metadata using getmodeldetails to verify the model's suitability.

Q: Does Metatext support multi-agent handoffs in OpenAI Agents SDK?

Yes, you can assign dataset management to one agent using createdatasetrecord and model execution to another using runmodelinference, letting them coordinate via the SDK's native MCP integration.

Q: Where does my NLP dataset record data go when using this server?

All dataset records sent via createdatasetrecord pass straight through Vinkius's secure, ephemeral V8 sandbox directly to your Metatext endpoint. No raw text payloads or training samples are ever stored on our servers.

Run NLP model inference and manage your datasets directly from your OpenAI Agents SDK production workflows using 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 OpenAI Agents SDK

Create your Vinkius account to connect Metatext to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Metatext inference inside OpenAI Agents SDK

This integration exposes the `run_model_inference` tool directly to your OpenAI Agents SDK runtime for instant predictions. Your agents can trigger text classification, extraction, or sentiment analysis on the fly without custom API glue code. The system monitors every inference call through the OpenAI dashboard to track costs and latency. Built-in guardrails validate the inputs before the agent fires the request, preventing malformed payloads from wasting your token budget.

Discover and query NLP models dynamically

The server uses `list_nlp_models` and `search_nlp_models` to let your agent query available models on the fly. Instead of hardcoding model IDs, your agent finds the best asset for the task based on real-time metadata. Once the agent finds a candidate, it calls `get_model_details` to verify the model architecture and training history. This metadata helps specialized agents decide whether to handle a task themselves or hand it off to a different agent.

Manage training datasets directly from agent runs

This toolset lets your agent inspect and append data using `list_nlp_datasets` and `create_dataset_record`. When your agent flags an edge case or a low-confidence prediction, it writes that record back to your training set instantly. You can also use `list_dataset_records` and `get_dataset_details` to let your agent audit existing data before starting a run. This closes the loop between production agent runs and dataset curation without leaving your MCP setup.

Setup guide

Set up Metatext MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Metatext tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Metatext tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Metatext tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Metatext Agent",
            instructions="You have access to Metatext tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK, spin up the server, and pass the HTTP streamable URL to your agent constructor. The SDK auto-discovers all ten tools, making them immediately available for your agent to call.

Yes, the agent can call `search_nlp_models` to locate specific models based on task requirements. It can then pull full metadata using `get_model_details` to verify the model's suitability.

Yes, you can assign dataset management to one agent using `create_dataset_record` and model execution to another using `run_model_inference`, letting them coordinate via the SDK's native MCP integration.

Set the tool caching flag to true when initializing your MCP Server connection. This prevents the SDK from refetching the tool definitions on every single turn, reducing startup latency.

All dataset records sent via `create_dataset_record` pass straight through Vinkius's secure, ephemeral V8 sandbox directly to your Metatext endpoint. No raw text payloads or training samples are ever stored on our servers.

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