How to Use the Browse AI MCP in Pydantic AI

Q: How do I load the Browse AI MCP Server into Pydantic AI?

Install the slim package with the mcp extra. Instantiate MCPToolset pointing to your Vinkius HTTP URL, and pass it in the toolsets list of your Agent.

Q: How do I run a specific Browse AI robot with Pydantic AI?

Your agent calls runrobot with the required parameters. The resulting task ID is checked, and the raw data fetched via gettask is parsed directly into your Pydantic model.

Get type-safe web scraping data from Browse AI validated at runtime by your Pydantic AI agent using this 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 Browse AI MCP to Pydantic AI

Create your Vinkius account to connect Browse 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 Browse AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Validated Scraping Tasks with Pydantic AI

Your agent triggers extraction using `run_robot` and retrieves the results using `get_task`. Pydantic AI enforces strict runtime validation on the returned JSON, ensuring that the scraped website fields match your Python schemas exactly. If Browse AI encounters a layout change that corrupts the expected JSON structure, the agent fails loudly. This prevents corrupt data from polluting your database, letting you catch extraction errors during execution.

Type-Safe Bulk Run and Monitor Management

Manage your recurring extraction tasks by calling `create_monitor` and listing them via `list_monitors`. Every payload returned from `get_bulk_run` or `list_bulk_runs` is validated against your Pydantic models before your code processes it. This runtime guarantee makes your scraping pipeline incredibly stable. Your agent can confidently parse hundreds of rows of scraped data, knowing that any missing fields or incorrect types will trigger immediate validation errors.

Validate System Status via Pydantic AI MCP Server

Before executing complex operations, the agent checks queue health with `get_system_status` and lists available extraction bots using `list_robots`. The tool responses are verified against strict internal models to ensure API consistency. By calling `get_robot`, your agent gets verified configuration metadata. Because Pydantic AI is model-agnostic, you can switch from Anthropic to OpenAI without changing your validation logic or your configuration.

Setup guide

Set up Browse 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": {
        "browse-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Browse 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 Browse AI. 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 Browse 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 Browse AI MCP in Pydantic AI

Install the slim package with the mcp extra. Instantiate `MCPToolset` pointing to your Vinkius HTTP URL, and pass it in the `toolsets` list of your `Agent`.

Pydantic AI will raise a validation error instantly. This prevents your agent from processing broken web data and ensures your pipeline only handles clean, structured outputs.

Yes, Pydantic AI supports both Streamable HTTP and SSE transports. You can configure your `MCPToolset` to connect to your Vinkius endpoint using either protocol.

Your agent calls `run_robot` with the required parameters. The resulting task ID is checked, and the raw data fetched via `get_task` is parsed directly into your Pydantic model.

All extracted text, page screenshots, and scraping configurations are isolated within the Vinkius V8 sandbox. Pydantic AI validates the data locally in your memory space, meaning sensitive credentials never leak outside your execution environment.

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