How to Use the AI21 Studio MCP in OpenAI Agents SDK

Q: Can AI21 Studio handle embedding large datasets in OpenAI Agents SDK?

You pass text arrays to embedtexts and define them as documents or queries. The server returns the vectors, which your agent can then store in its preferred database.

Plug AI21 Studio directly into your OpenAI Agents SDK production pipeline for reliable text processing and generation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI21 Studio MCP to OpenAI Agents SDK

Create your Vinkius account to connect AI21 Studio 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 AI21 Studio with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Jamba completions in OpenAI Agents SDK

Use the `chat_completion` tool to pull responses from Jamba-1.5 models directly into your agent's decision loop. It handles the JSON array of messages, so your agent stays in sync with the model's output without extra parsing. This setup works inside your `MCPServerStreamableHttp` constructor. By setting `cacheToolsList=True`, your production agent keeps its latency low while calling Jamba endpoints.

Refine agent output with AI21 Studio tools

Clean up your agent's drafts using the `grammar_corrections` tool before showing them to users. It catches errors that standard logic might miss, giving your agent a polished professional tone. Running `paraphrase` on agent-generated content allows you to switch between styles like casual or formal. It forces the agent to rewrite its own output to match the specific needs of your end-user.

Process long documents with AI21 Studio

Feed large blocks of text into `summarize` to extract the core points before your agent acts on the data. It respects API limits while providing concise summaries that fit neatly into your agent's context window. Use `segmentation` to break down messy input into clean sentences. This ensures your agent processes incoming data in logical chunks rather than one giant, unformatted string.

Setup guide

Set up AI21 Studio 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 AI21 Studio tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AI21 Studio tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AI21 Studio 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="AI21 Studio Agent",
            instructions="You have access to AI21 Studio 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 AI21 Studio. 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 AI21 Studio 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 AI21 Studio MCP in OpenAI Agents SDK

Yes, every tool response returns raw data that the OpenAI Agents SDK guardrails can validate immediately. You define the schema, and the agent rejects any malformed output before it hits your production logs.

Vinkius handles authentication through a single endpoint token. You don't need to expose your API keys in your environment variables, keeping your agent's credentials isolated from the application logic.

You pass text arrays to `embed_texts` and define them as documents or queries. The server returns the vectors, which your agent can then store in its preferred database.

The HTTP transport provides a consistent connection for your agent. Since it's managed by the Vinkius infrastructure, you avoid the typical headaches of local server maintenance.

Your text is processed only for the requested task, such as summarization or grammar checks. None of your input content is used to train third-party models, keeping your production data 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