How to Use the Microlink MCP in Pydantic AI

Q: How do I register Microlink MCP tools within Pydantic AI?

Use the MCPToolset class to connect to your MCP Server. Pass this toolset directly into the Agent constructor to expose tools like extractmetadata to your model.

Extract type-safe web metadata, PDFs, and screenshots with Pydantic AI agents that fail loudly on invalid data.

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 Pydantic AI

Create your Vinkius account to connect Microlink to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe web scraping with the Microlink MCP Server

Validating web schemas at runtime is automatic when combining Pydantic AI with `extract_metadata` to fetch structured web data. If a website returns malformed Open Graph tags or missing author fields, your agent catches the validation error instantly. This guarantees that only clean, structured web data enters your downstream application logic.

Validate screenshots and PDFs before saving

Generating and verifying visual documents is straightforward when your Pydantic AI agents call `take_screenshot` or `generate_pdf`. Because the framework is model-agnostic, you can use any LLM to inspect the visual files. The agent uses the `advanced_query` tool to customize the viewport, ensuring that the generated assets match your application's layout requirements.

Run validated performance audits using Pydantic AI

Retrieving structured performance metrics with `get_insights` lets Pydantic AI validate that the response contains all required core web vitals. This setup is designed for developers who value correctness over raw speed. If the audit data is incomplete, the framework raises a clear validation error, preventing your agent from making decisions based on partial information.

Setup guide

Set up Microlink MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "microlink-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Microlink tools.",
)

result = await agent.run("List recent Microlink transactions")
print(result.output)

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 Pydantic AI

Use the `MCPToolset` class to connect to your MCP Server. Pass this toolset directly into the `Agent` constructor to expose tools like `extract_metadata` to your model.

The framework will raise a validation error immediately. This prevents silent failures and ensures your agent only works with data that matches your defined Pydantic models.

Yes, the framework is model-agnostic. You can connect your toolset to agents running local models, allowing them to invoke `take_screenshot` or `get_insights` exactly like commercial models would.

No, Vinkius hosts and manages the server for you. Your agent connects directly to the managed HTTP endpoint using your single access token, handling all tool execution in the cloud.

All target URLs, PDFs, and screenshots are processed in isolated, ephemeral environments. Pydantic AI receives the validated data over a secure connection, and Vinkius never stores the extracted web metadata or generated files after the request 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