How to Use the Parsio MCP in OpenAI Agents SDK

Q: How do I set up Parsio with the OpenAI Agents SDK?

Install the package with pip, instantiate MCPServerStreamableHttp with your Vinkius endpoint, which hosts the MCP Server, and pass it to the Agent constructor. Set cacheToolsList=True to speed up runtimes.

Q: Can my OpenAI Agents SDK agent run async extractions?

Yes, your agent can call extractdatafromtextasync and then poll getparseddocumentresult to keep the main thread free for other operations.

Get clean, parsed email and PDF data directly into your OpenAI Agents SDK workflows without writing custom extraction scripts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Parsio MCP to OpenAI Agents SDK

Create your Vinkius account to connect Parsio to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Parsio with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Pull data from files directly with OpenAI Agents SDK

Stop writing custom regex to extract shipping numbers or invoice totals from random PDFs with this MCP Server. Your agent can call `extract_data_from_file_sync` to parse incoming files instantly, getting back clean JSON that maps directly to your agent's state. For high-volume operations where you don't want to block the main agent thread, look, here is the thing: use `extract_data_from_file_async`. The agent triggers the run and checks back later using `get_parsed_document_result` while executing other tasks in the background.

Manage parsing mailboxes programmatically

Set up pipelines on the fly by letting your agent call `create_mailbox` when a new vendor joins your system. The agent can inspect existing configurations with `list_mailboxes` to route incoming documents to the correct parser. To keep your backend in sync, the agent can call `list_mailbox_webhooks` to verify where Parsio is sending real-time updates. This keeps your agentic workflow aware of data routing without hardcoded endpoints.

Audit historical data inside your MCP Server pipeline

When an agent needs to resolve a billing dispute or verify a past transaction, it calls `list_parsed_data_history` to pull past document outputs. This gives your agent a complete paper trail of extracted invoice data directly inside the chat window. You can also check template metadata with `get_template_details` to verify which parsing rules were applied to older documents. It makes debugging parsing discrepancies straightforward for your agentic system.

Setup guide

Set up Parsio 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 Parsio tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with pip, instantiate `MCPServerStreamableHttp` with your Vinkius endpoint, which hosts the MCP Server, and pass it to the Agent constructor. Set `cacheToolsList=True` to speed up runtimes.

Yes, your agent can call `extract_data_from_text_async` and then poll `get_parsed_document_result` to keep the main thread free for other operations.

The server uses Parsio's backend templates, which you can list with `list_mailbox_templates`, to extract structured tables into clean JSON arrays.

You control tool access through your OpenAI Agents SDK configuration by filtering the tool list before passing it to the agent instance.

All document parsing happens in Vinkius's secure, ephemeral V8 sandboxes. Your raw emails and PDFs are processed strictly to return structured JSON, and no data is stored on Vinkius servers after the execution completes.

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