AI21 Studio MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect AI21 Studio through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="AI21 Studio Assistant",
instructions=(
"You help users interact with AI21 Studio. "
"You have access to 7 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from AI21 Studio"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About AI21 Studio MCP Server
Connect AI21 Studio to your AI agent and unlock access to the powerful Jamba models alongside a suite of highly-specialized linguistic tools. Give your agent the ability to process texts with enterprise-grade precision via natural conversation.
The OpenAI Agents SDK auto-discovers all 7 tools from AI21 Studio through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries AI21 Studio, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Chat & Instruct — Generate chat completions natively utilizing AI21's advanced Jamba models
- Summarization — Produce accurate and concise summaries of long text payloads instantly
- Paraphrasing — Rewrite text passages into different specific styles (general, casual, formal, long, short)
- Grammar & Spelling — Catch and correct grammatical and spelling errors using AI21's dedicated correction engine
- Text Segmentation — Split continuous text into distinct sentences based on complex grammatical boundaries
- Embeddings — Convert pieces of text into high-dimensional numerical embeddings for RAG workflows
The AI21 Studio MCP Server exposes 7 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect AI21 Studio to OpenAI Agents SDK via MCP
Follow these steps to integrate the AI21 Studio MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 7 tools from AI21 Studio
Why Use OpenAI Agents SDK with the AI21 Studio MCP Server
OpenAI Agents SDK provides unique advantages when paired with AI21 Studio through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
AI21 Studio + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the AI21 Studio MCP Server delivers measurable value.
Automated workflows: build agents that query AI21 Studio, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries AI21 Studio, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through AI21 Studio tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query AI21 Studio to resolve tickets, look up records, and update statuses without human intervention
AI21 Studio MCP Tools for OpenAI Agents SDK (7)
These 7 tools become available when you connect AI21 Studio to OpenAI Agents SDK via MCP:
chat_completion
g., jamba-1.5-large, jamba-1.5-mini) and the conversation messages as a JSON array. Generate chat completions using AI21 Jamba models
embed_texts
Pass a JSON array of texts and specify whether they are for "query" or "document". Generate text embeddings using AI21 Studio embeddings
grammar_corrections
Perform Grammatical Error Correction (GEC) on text
paraphrase
Available styles: general, casual, formal, long, short. Paraphrase text using AI21 Studio
segmentation
Segment texts into sentences using AI21 Studio process
summarize
Text length must depend on API limits. Summarize long texts using AI21 Studio process
text_completion
Generate text completions using AI21 Studio models
Example Prompts for AI21 Studio in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with AI21 Studio immediately.
"Paraphrase this paragraph into a highly formal tone."
"Run a grammatical error correction over my draft and output the fixed version."
"Segment this long block of text into individual sentences."
Troubleshooting AI21 Studio MCP Server with OpenAI Agents SDK
Common issues when connecting AI21 Studio to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
AI21 Studio + OpenAI Agents SDK FAQ
Common questions about integrating AI21 Studio MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect AI21 Studio with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect AI21 Studio to OpenAI Agents SDK
Get your token, paste the configuration, and start using 7 tools in under 2 minutes. No API key management needed.