How to Use the Metatext MCP in AutoGen

Q: How do AutoGen agents access Metatext tools?

You register the tools with the AssistantAgent using the AutoGen MCP adapter. This exposes tools like runmodelinference so any agent in the group can call them during a conversation.

Q: Can one AutoGen agent train a model and another verify it on Metatext?

Yes. Agents can use listmodeldeployments to find newly deployed models and then run runmodelinference to test them against a set of validation records.

Build multi-agent AutoGen debates to validate NLP models and manage Metatext datasets.

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 AutoGen

Create your Vinkius account to connect Metatext 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 Metatext with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate model inference through agent debates

The `run_model_inference` tool lets your AutoGen agents run predictions and debate the results before making a final decision. For example, a classifier agent can run an inference call, while a critic agent reviews the confidence score and demands a second look if the threshold is too low. This consensus-driven approach keeps your automated decisions reliable. Because the prediction tool is shared across the conversation, any agent in the group can trigger a run when they need hard data to back up their argument. It turns static model outputs into collaborative decisions.

Manage training datasets via collaborative agents

The `create_dataset_record` tool allows your data-curator agents to write verified text samples directly back to your datasets. During a multi-agent conversation, one agent can flag an ambiguous user input, a second agent can resolve the label, and a third agent can commit the clean record to your dataset. This automates the data cleaning process. Your agents can also use `get_dataset_details` to verify that the dataset schema matches the incoming data format. If there is a mismatch, the developer agent can be alerted to update the pipeline.

Monitor deployments with this MCP Server

The `list_model_deployments` and `list_nlp_models` tools give your operations agents real-time visibility into your active infrastructure. An orchestrator agent can query the active deployments list to verify that a model is live before assigning it to a worker agent. If a model is missing, the agent can search for alternatives using `search_nlp_models`. This keeps your multi-agent workflows running smoothly even when underlying models are being redeployed or updated. The agents adapt to the active state of your account without hardcoded routing.

Setup guide

Set up Metatext 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 Metatext 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="Metatext_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Metatext 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="Metatext_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Metatext 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 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 AutoGen

You register the tools with the `AssistantAgent` using the AutoGen MCP adapter. This exposes tools like `run_model_inference` so any agent in the group can call them during a conversation.

Yes. Agents can use `list_model_deployments` to find newly deployed models and then run `run_model_inference` to test them against a set of validation records.

The server runs in a sandboxed environment on Vinkius that handles concurrent JSON-RPC requests, ensuring that multiple agents debating in parallel won't block each other's tool calls.

No. The MCP adapter automatically converts the tool schemas, meaning outputs from tools like `get_model_details` are delivered to your agents in clean, structured text they can read immediately.

Your dataset records and inference payloads pass through a secure, ephemeral V8 isolate. Vinkius does not log or persist any of the text content, keeping your intellectual property safe and 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