How to Use the Microlink MCP in OpenAI Agents SDK

Q: How do I configure the Microlink MCP Server in my OpenAI Agents SDK pipeline?

Install the package, then use MCPServerStreamableHttp to connect to the hosted MCP endpoint. Pass the server instance directly into your Agent constructor's mcpservers list. Your agents will auto-discover tools like extractmetadata immediately.

Build production-grade OpenAI Agents SDK systems that turn live websites into clean data, PDFs, and screenshots with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Microlink MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run secure web audits using the Microlink MCP Server

Calling `get_insights` through this MCP Server pulls deep performance metrics and tech stacks directly into your OpenAI Agents SDK guardrail validation loop. You don't have to worry about raw, unparsed junk breaking your agent handoffs. The tool returns clean, structured performance data so your specialized agent can decide whether to proceed or hand the task back to the supervisor.

Generate clean PDFs and screenshots on the fly

Generating visual assets like PDFs and screenshots is simple when your OpenAI Agents SDK workflow triggers `take_screenshot` or `generate_pdf` during execution. You configure the viewport, custom margins, or page scale directly in the agent's run parameters. The agent handles the browser rendering in the background and delivers a clean file stream, keeping your production pipelines running without spinning up a separate headless browser cluster.

Extract structured metadata with OpenAI Agents SDK

Extracting structured JSON from target URLs is handled automatically when your agents call `extract_metadata` or `advanced_query`. The OpenAI Agents SDK automatically registers these MCP capabilities with zero configuration. Because the SDK validates agent actions before they fire, you can enforce strict policies on which URLs your agents are allowed to query.

Setup guide

Set up Microlink 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 Microlink tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package, then use `MCPServerStreamableHttp` to connect to the hosted MCP endpoint. Pass the server instance directly into your Agent constructor's `mcp_servers` list. Your agents will auto-discover tools like `extract_metadata` immediately.

Yes, you can control tool access at the agent definition level. If you only want a specific agent to generate visual files, only expose `take_screenshot` or `generate_pdf` to that agent while hiding the query tools.

The SDK relies on your Vinkius endpoint token to manage authentication and rate limits. If you hit a limit during `advanced_query` execution, the SDK receives a clean error code, allowing your agent's error-handling loop to retry the request.

No, the server handles all browser rendering on its own infrastructure. Your agent simply calls `take_screenshot` and receives the finished image, saving you from deploying Puppeteer or Playwright in your Python environment.

All target URLs, generated PDFs, and screenshots are processed inside ephemeral, zero-trust V8 isolate sandboxes. Vinkius does not store the raw web metadata or visual files after they are returned to your Python environment, keeping your automated web runs private.

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