How to Use the Extracta MCP in AutoGen

Q: Can AutoGen agents change Extracta schemas dynamically?

Yes, an agent can call updateextraction if it detects that the current schema is missing critical fields during their conversation.

Q: What happens if AutoGen agents disagree on an Extracta classification?

They can call viewclassification to inspect the rules and run createclassification again with a refined schema to resolve the conflict.

Q: How do I clean up completed extractions?

Your agents can call deleteextraction once they agree the processing is complete. This ensures no orphaned extraction processes remain active.

Let AutoGen agents debate and verify structured document data using the Extracta MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Extracta MCP to AutoGen

Create your Vinkius account to connect Extracta 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 Extracta with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Settle document type disputes in AutoGen

The `create_classification` tool allows one of your AutoGen agents to define categories and submit a document for classification. A second agent can then call `get_classification_results` to verify the predicted type. This multi-agent debate ensures high-accuracy classification before any data extraction begins. If the agents disagree on the category, they negotiate a fallback classification schema.

Audit Extracta MCP Server fields via agent consensus

The `get_results` tool retrieves the extracted JSON data so your AutoGen agents can review it. One agent inspects the raw numbers while another checks compliance against your business rules. This division of labor prevents extraction errors from slipping into your database. They must agree on the validity of the data before the conversation terminates.

Let agents update schemas during execution

The `update_extraction` tool lets a supervising AutoGen agent modify extraction fields when a run returns incomplete data. If a peer agent flags a missing field, the supervisor updates the schema dynamically. This self-correcting behavior keeps your pipeline running without manual developer intervention. They adjust the target fields on the fly and re-run the extraction.

Setup guide

Set up Extracta 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 Extracta 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="Extracta_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Extracta 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 Extracta. 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 Extracta 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 Extracta MCP in AutoGen

One agent uploads a document while the MCP server handles the file transfer. Another agent polls `get_results` to retrieve the data, allowing them to discuss the extracted JSON to verify its accuracy.

Yes, an agent can call `update_extraction` if it detects that the current schema is missing critical fields during their conversation.

They can call `view_classification` to inspect the rules and run `create_classification` again with a refined schema to resolve the conflict.

Your agents can call `delete_extraction` once they agree the processing is complete. This ensures no orphaned extraction processes remain active.

Your MCP server handles document URLs and classification schemas over secure, ephemeral channels directly to the processing API. No document content is stored within agent conversation logs, protecting your proprietary business files.

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