How to Use the Extracta MCP in OpenAI Agents SDK

Q: How do I handle document polling in Extracta with OpenAI Agents SDK?

Call uploadfileurl to get a document ID, then write a basic loop that checks getresults until the status shows complete. The SDK manages this state asynchronously so your agent doesn't block other threads.

Q: Can I run classification tasks using Extracta and OpenAI Agents SDK?

Yes, use createclassification to set up your categories and getclassificationresults to read the predicted type. This lets your OpenAI agents route files to different sub-agents based on whether they are receipts or contracts.

Q: How does the Extracta MCP Server handle schema updates in OpenAI Agents SDK?

The server exposes updateextraction which lets your agent modify the expected fields directly. Your OpenAI agent can dynamically adjust to new document formats without requiring any manual code changes.

Q: Can I clean up old extraction configurations?

Use the deleteextraction tool to remove configurations you no longer need. Once deleted, any subsequent file uploads to that specific extraction ID will immediately fail.

Turn documents into structured JSON inside your OpenAI Agents SDK workflows using managed MCP tools.

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 OpenAI Agents SDK

Create your Vinkius account to connect Extracta 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 Extracta with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Extracta schemas directly inside OpenAI Agents SDK

`create_extraction` is the tool your OpenAI agent uses to define what fields it needs to pull from raw files. This sets up an MCP schema for invoice dates or line items, giving your agent a direct endpoint to target. Your Python agent calls `upload_file_url` to send documents over, then polls `get_results` to grab the clean JSON. The OpenAI agent handles the polling loop natively, pausing execution until the extraction is complete.

Automatic document classification with strict guardrails

`create_classification` lets your agent route incoming documents to the correct processing pipeline. It sends the document URL, gets the type back, and triggers the next agent handoff. The agent uses `get_classification_results` to verify if a file is an invoice or a contract before running extraction rules. If the classification fails, OpenAI guardrails block further processing to save API credits.

Dynamic mapping updates without redeploying code

`update_extraction` allows your agent to tweak extraction rules on the fly when document layouts change. It updates the schema in real-time without you having to restart your Python application. The agent checks current rules with `view_extraction` to see what fields are active. If a field is missing, it updates the configuration and runs the extraction again.

Setup guide

Set up Extracta 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 Extracta tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Extracta tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Extracta 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="Extracta Agent",
            instructions="You have access to Extracta 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 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 OpenAI Agents SDK

Call `upload_file_url` to get a document ID, then write a basic loop that checks `get_results` until the status shows complete. The SDK manages this state asynchronously so your agent doesn't block other threads.

Yes, use `create_classification` to set up your categories and `get_classification_results` to read the predicted type. This lets your OpenAI agents route files to different sub-agents based on whether they are receipts or contracts.

The server exposes `update_extraction` which lets your agent modify the expected fields directly. Your OpenAI agent can dynamically adjust to new document formats without requiring any manual code changes.

Use the `delete_extraction` tool to remove configurations you no longer need. Once deleted, any subsequent file uploads to that specific extraction ID will immediately fail.

Extracta processes your uploaded document URLs to extract text and run classifications, storing temporary files during processing. The connection from your OpenAI agent to Vinkius is protected by zero-trust sandboxing, meaning your document bytes are isolated and wiped after the MCP job finishes.

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