How to Use the Affinda MCP in OpenAI Agents SDK

Q: How do I connect Affinda to the OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to the mcpservers array in your Agent constructor.

Q: Can OpenAI Agents SDK validate Affinda document types?

Yes. Your agent runs listdocumenttypes to verify supported models like passports or invoices before attempting extraction. This triggers the SDK's built-in guardrails if a file type mismatches.

Q: Does the Affinda MCP Server support async operations in OpenAI?

You wrap the server connection in an async with context manager. The createdocument tool defaults to waiting synchronously for the parsing to finish, but the SDK handles the network request asynchronously.

Connect Affinda to the OpenAI Agents SDK for production-ready document extraction with built-in safety guardrails and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinda MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Document Parsing with OpenAI Agents

The `create_document` tool feeds PDFs directly into your OpenAI agent system while applying your defined safety constraints. You pass a public URL, and the SDK handles the synchronous wait automatically. Production deployments need reliable state tracking. When an agent triggers `get_document`, the OpenAI dashboard logs the exact JSON payload extracted from that invoice or resume, making debugging straightforward.

Manage Workspaces and Types via MCP Server

Calling `list_document_types` exposes the exact parsing models your Affinda account supports right inside your agent's context. Your routing agents use this to hand off specific files to specialized extraction agents. Sorting through client folders requires the `list_workspaces` tool. The agent reads the container structures before deciding where to drop newly processed files.

Track Processing Status Across Agents

Agents monitor batch progress using the `list_documents` tool to pull processing states across an entire workspace. This prevents your system from acting on incomplete data before handoffs occur. Setting `cacheToolsList=True` in your `MCPServerStreamableHttp` configuration keeps these polling operations fast. The agent focuses on reading the structured output instead of repeatedly discovering the tool schema.

Setup guide

Set up Affinda 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 Affinda tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL and pass it to the `mcp_servers` array in your Agent constructor.

Yes. Your agent runs `list_document_types` to verify supported models like passports or invoices before attempting extraction. This triggers the SDK's built-in guardrails if a file type mismatches.

You wrap the server connection in an `async with` context manager. The `create_document` tool defaults to waiting synchronously for the parsing to finish, but the SDK handles the network request asynchronously.

The SDK traces every tool call automatically. Check your OpenAI dashboard to inspect the exact JSON returned by `get_document` and see why an agent failed to read a specific field.

Vinkius isolates every connection in an ephemeral V8 sandbox. Your sensitive PDFs and extracted JSON payloads pass directly to your agent system without persisting on our infrastructure.

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