How to Use the AI21 Labs MCP in OpenAI Agents SDK

Q: How do I install the AI21 Labs MCP Server for OpenAI Agents SDK?

Run pip install openai-agents first. Then set up an MCPServerStreamableHttp connection using your Vinkius URL. Pass it via mcpservers=server when creating your agent.

Q: Does OpenAI Agents SDK cache the AI21 Labs tools?

Yes, you can enable caching. Set cacheToolsList=True in your server parameters. This stops the agent from fetching the schema on every single turn.

Connect the AI21 Labs MCP Server to your OpenAI Agents SDK system. Run Jamba models and text processors behind strict production guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI21 Labs MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run AI21 Labs inside the OpenAI Agents SDK

Hook up Israeli-built frontier models right into your multi-agent setups. You drop the Vinkius endpoint into your agent constructor. The SDK automatically discovers every available tool on the server. Need a specialized writer agent? Give it `ai21_paraphrase_text` and `ai21_grammar_correction`. You get precise text rewriting while OpenAI's guardrails validate the inputs and outputs before anything hits the end user.

Process massive documents with Jamba

Jamba handles long context windows differently than transformer-only models. You pass the text. The model reads it all without losing the plot in the middle. When you trigger `ai21_summarize_text` or `ai21_segment_text`, your agent breaks down massive corporate documents. The built-in tracing on the OpenAI dashboard shows exactly how the agent chopped up the text and what the server returned.

RAG without the vector database

Sometimes you do not need a massive retrieval pipeline. You just have a few files and need exact answers. Upload the documents. Then have your agent call `ai21_contextual_answers`. It checks the exact context you provided and replies based strictly on those files. You can manage the file lifecycle directly using `ai21_list_files` and `ai21_delete_file` when the session ends.

Setup guide

Set up AI21 Labs 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 Labs tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AI21 Labs 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 Labs 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 Labs Agent",
            instructions="You have access to AI21 Labs 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 Labs. 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 Labs 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 Labs MCP in OpenAI Agents SDK

Run `pip install openai-agents` first. Then set up an `MCPServerStreamableHttp` connection using your Vinkius URL. Pass it via `mcp_servers=[server]` when creating your agent.

Yes, you can enable caching. Set `cacheToolsList=True` in your server parameters. This stops the agent from fetching the schema on every single turn.

The server gives you direct access to the Jamba family, including jamba-1.5-mini. Call the `ai21_chat_completion` endpoint to start generating responses.

You handle that through agent handoffs. Create a specialized agent that only has access to the specific rewriting or summarization endpoints you want it to use.

When you upload PDFs or docs for contextual answering, they sit in an isolated V8 sandbox. Vinkius tears down the entire environment the second your session ends. Zero persistent storage of your corporate documents.

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