How to Use the Hyperbrowser (Web Infra for AI) MCP in Pydantic AI

Q: How do I register the Hyperbrowser (Web Infra for AI) MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance to your Agent constructor's toolsets argument to register the MCP tools.

Q: Can I run async scraping jobs with the Hyperbrowser (Web Infra for AI) MCP Server and Pydantic AI?

Yes, you can initiate a job with startscrape and poll for completion using getscrapejob. This pattern allows your agent to handle massive scraping tasks without blocking the main event loop.

Q: How do I check the status of a running browser session?

Use getsession to return detailed health and duration metrics for any active connection. Your Pydantic AI agent can use this data to determine if a session needs to be restarted or terminated.

Run type-safe web automation with Pydantic AI, validating every scraped HTML payload and browser state at runtime via our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperbrowser (Web Infra for AI) MCP to Pydantic AI

Create your Vinkius account to connect Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe web extraction in Pydantic AI

`extract_data` forces the cloud browser to parse web content directly into your defined Pydantic schemas. If the webpage layout changes and returns unexpected data, your Pydantic AI agent catches the validation error immediately. This strict runtime validation prevents malformed web data from silently corrupting your database. You get clean, typed data structures instead of raw, unpredictable JSON strings.

Deterministic browser state management

`create_session` instantiates a remote browser session with explicit configurations that you can define using Python types. This guarantees that parameters like proxies or screen resolution match your application's requirements. To keep your resource usage predictable, `stop_session` kills the remote instance the moment your agent finishes its task. You can verify the cleanup by calling `list_sessions` and asserting that no background sessions remain active.

Execute verified JavaScript inside Pydantic AI agents

`run_script` executes custom JavaScript inside the remote browser and returns the evaluation result directly to your agent. Pydantic AI validates the return type of the script execution at runtime to ensure type safety. If you just need a visual snapshot, `page_screenshot` returns image metadata that maps cleanly to your python models. This is ideal for building visual testing pipelines that require guaranteed structure.

Setup guide

Set up Hyperbrowser (Web Infra for AI) 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": {
        "hyperbrowser-web-infra-for-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Hyperbrowser (Web Infra for AI) 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 Hyperbrowser. 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 Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) MCP in Pydantic AI

Install pydantic-ai-slim[mcp] and use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance to your Agent constructor's toolsets argument to register the MCP tools.

Pydantic AI will raise a validation error at runtime. This prevents your agent from proceeding with corrupted or incomplete data, making it easy to catch breaking changes on target websites.

Yes, you can initiate a job with `start_scrape` and poll for completion using `get_scrape_job`. This pattern allows your agent to handle massive scraping tasks without blocking the main event loop.

Use `get_session` to return detailed health and duration metrics for any active connection. Your Pydantic AI agent can use this data to determine if a session needs to be restarted or terminated.

Your active sessions, cookies, and raw page HTML are processed in secure, isolated sandboxes. Vinkius handles the underlying endpoint authentication, ensuring that sensitive web data never leaks outside your execution context.

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