Can my agent create a new data extraction setup with custom fields?

Yes. Use the 'create_extraction' tool. Provide a JSON schema defining the fields you expect (e.g., 'total_amount', 'vendor_name'). The agent will return a new extractionId for document processing.

How do I process a PDF document using a specific extraction ID via chat?

Use the 'upload_file_url' tool. Provide the extractionId and the public URL of your PDF. The agent will trigger the workflow and return a documentId, which you can use with 'get_results' to fetch the data.

Can I see the predicted document type and confidence score through the agent?

Absolutely. Use the 'get_classification_results' tool with the document and classification IDs. The agent will retrieve the AI-predicted label (e.g., 'Invoice') and the confidence score for the processed file.

Extracta MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Extracta
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Extracta through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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="Extracta Assistant",
            instructions=(
                "You help users interact with Extracta. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Extracta"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Extracta MCP Server

Connect your Extracta.ai account to any AI agent and take full control of your automated data extraction and document classification through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Extracta through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Extracta, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Extraction Orchestration — Create and configure new data extraction processes by defining JSON schemas for fields like dates, amounts, and item descriptions natively
Live Document Processing — Submit publicly accessible file URLs (PDF, JPG, PNG) to trigger asynchronous extraction workflows and retrieve structured JSON data seamlessly
AI Classification — Set up document classification rules to automatically sort documents into types like invoices, receipts, or contracts based on AI predictions
Result Auditing — Retrieve extraction status and finalized structured data for specific documents, evaluating confidence scores and predicted categories flawlessly
Batch History Monitoring — Fetch paginated lists of previously extracted documents and their associated data payloads to track historical processing limitlessly
Configuration Mutation — Update existing extraction settings and mapping rules without creating new endpoints to refine your data parsing logic
Workflow Management — View and manage extraction and classification configurations, including configured fields and webhook settings securely

The Extracta MCP Server exposes 10 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 Extracta to OpenAI Agents SDK via MCP

Follow these steps to integrate the Extracta 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 10 tools from Extracta

Why Use OpenAI Agents SDK with the Extracta MCP Server

OpenAI Agents SDK provides unique advantages when paired with Extracta 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

Extracta + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Extracta MCP Server delivers measurable value.

Automated workflows: build agents that query Extracta, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Extracta, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Extracta tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Extracta to resolve tickets, look up records, and update statuses without human intervention

Extracta MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Extracta to OpenAI Agents SDK via MCP:

create_classification

g. invoice, receipt, contract). Pass JSON schema defining categories. Create a new Extracta document classification setup

create_extraction

g. language, format, expected fields like invoice_date, total_amount). Returns a new extractionId used for subsequent document processing. Create a new Extracta.ai data extraction process

delete_extraction

Subsequent uploads to this extractionId will fail. Delete an Extracta.ai extraction process

get_batch_results

Get bulk historical results from an Extraction process

get_classification_results

Get the predicted document category from Extracta

get_results

If not completed, it will indicate processing status. Get extraction results for a specific document

update_extraction

Modifies mapping rules without needing to create a new endpoint. Update an existing Extracta extraction configuration

upload_file_url

Returns a documentId. Use ea.get_results to poll for extracted data. Upload a document URL to Extracta for processing

view_classification

View details of an existing document classification process

view_extraction

View configuration of an existing Extracta extraction process

Example Prompts for Extracta in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Extracta immediately.

"Create an extraction process for invoices with fields: date, vendor, total"

"Extract data from this receipt URL: https://example.com/receipt.pdf"

"What type of document is doc_789 according to my classification rules?"

Troubleshooting Extracta MCP Server with OpenAI Agents SDK

Common issues when connecting Extracta to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Extracta + OpenAI Agents SDK FAQ

Common questions about integrating Extracta MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.