How to Use the Microlink MCP in AutoGen

Let your AutoGen agents debate and execute web tasks, from capturing screenshots to auditing performance metrics.

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 AutoGen

Create your Vinkius account to connect Microlink to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable consensus-driven web auditing

`get_insights` provides the raw performance data that your AutoGen agents need to debate site quality. An AutoGen performance agent analyzes the Microlink response speed while a design agent reviews the layout. They deliberate over the Microlink metrics before compiling a final optimization report inside AutoGen. This collaborative AutoGen loop ensures you get a balanced Microlink analysis without manual intervention.

Capture visual proof with AutoGen MCP Server tools

`take_screenshot` captures the visual state of a webpage at any point during an AutoGen conversation. One AutoGen agent triggers the Microlink screenshot, and a critic agent inspects it for visual bugs. This MCP Server tool supports element-specific targeting and device emulation for AutoGen workflows. Your AutoGen agents coordinate the exact Microlink viewport parameters required for the test case.

Extract clean metadata for agent coordination

`extract_metadata` supplies structural web details to your AutoGen coordinator agent. The coordinator agent uses this Microlink information to delegate scraping or analysis tasks to specialized AutoGen sub-agents. Having clean Microlink JSON data prevents parsing errors from breaking the AutoGen conversation flow. The entire AutoGen multi-agent system stays aligned on verified web facts retrieved via Microlink.

Setup guide

Set up Microlink MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Microlink tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Microlink_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Microlink data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Microlink_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Microlink data")
    print(result.messages[-1].content)

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 AutoGen

Install the package and use the MCP server tools helper with your server's HTTP URL. Pass the returned tools list directly to your `AssistantAgent` constructor.

The agents look at the JSON schema for the tools and debate which parameters to set. Once they agree, the designated executor agent makes the call.

Yes. The server fully supports Streamable HTTP, allowing your agents to interact with the API across distributed network environments.

The error is returned to the active agent, which can then discuss the failure with other agents and attempt a corrected call.

The MCP Server operates on a zero-trust architecture where all performance insights and queries are processed in ephemeral sandboxes. Your target URLs and system data are never persisted.

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