How to Use the AI21 Labs MCP in AutoGen

Q: Can one AutoGen agent summarize text while another edits it using AI21 Labs?

Yes, you can assign ai21summarizetext to a summarizer agent and ai21textimprovements to an editor agent. They will pass messages back and forth to refine the document.

Q: How do AutoGen agents manage files using AI21 Labs?

An agent can call ai21listfiles to see what resources are available, then pass the file IDs to other agents. If a file is no longer needed, a cleanup agent calls ai21deletefile.

Let AutoGen agents debate text style, grammar, and summaries using specialized AI21 Labs tools.

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 AutoGen

Create your Vinkius account to connect AI21 Labs to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative copy editing with AutoGen

Set up a multi-agent debate where a copywriter agent drafts text using `ai21_chat_completion` and an editor agent critiques it. The editor agent calls `ai21_text_improvements` to suggest stylistic changes, pushing the writer to revise its draft. This workflow uses the MCP Server to resolve stylistic disagreements. If the agents can't agree on tone, a third auditor agent runs `ai21_paraphrase_text` to generate a neutral middle ground.

Multi-agent document analysis and segmentation

When analyzing large files, one AutoGen agent can run `ai21_segment_text` to break the document into topical chapters. It then assigns different chapters to specialized sub-agents for deeper analysis. Each sub-agent uses `ai21_summarize_text` to extract key insights from its assigned chapter. The main orchestrator agent compiles these summaries into a final report, ensuring no single agent gets overwhelmed by context limits.

Automated factual validation loops

Prevent hallucinations by setting up a validation agent that calls `ai21_contextual_answers` against uploaded reference files to verify statements in real time. This agent runs silently in the background of your conversation. If the verification agent finds a discrepancy, it queries `ai21_get_file` to check the source document's metadata. This consensus-driven approach ensures your team gets verified facts instead of guessed answers.

Setup guide

Set up AI21 Labs MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AI21 Labs tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AI21 Labs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AI21 Labs data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AI21 Labs_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AI21 Labs data")
    print(result.messages[-1].content)

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 AutoGen

You register the tools with the AutoGen AssistantAgent using the MCP adapter. This lets agents autonomously execute tools like `ai21_grammar_correction` during their conversations.

Yes, you can assign `ai21_summarize_text` to a summarizer agent and `ai21_text_improvements` to an editor agent. They will pass messages back and forth to refine the document.

An agent can call `ai21_list_files` to see what resources are available, then pass the file IDs to other agents. If a file is no longer needed, a cleanup agent calls `ai21_delete_file`.

Yes, multiple AutoGen agents can invoke different tools simultaneously. For example, one agent can run grammar checks while another segments text, speeding up your pipeline.

All conversational exchanges and file metadata processed through the server run inside ephemeral, isolated V8 instances. Vinkius ensures that once the multi-agent session terminates, all execution states and temporary data are completely wiped.

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