How to Use the Browserbear MCP in Pydantic AI

Q: How do I register the Browserbear toolset in Pydantic AI?

Initialize the MCPToolset with your Vinkius HTTP endpoint URL. Pass this toolset directly into the toolsets argument of your Pydantic AI Agent using the MCP protocol.

Validate your automated browser runs with strict runtime schemas using Pydantic AI and Browserbear.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbear MCP to Pydantic AI

Create your Vinkius account to connect Browserbear 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 Browserbear with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas on your Pydantic AI MCP Server runs

The `get_run` tool retrieves the exact execution status and output data of your browser automations. When using Pydantic AI, this output is validated against strict Python type hints, ensuring your agent never processes malformed scraping results. If a browser run returns unexpected data, your application raises a validation error immediately. This prevents silent failures from corrupting your production databases.

Audit automation performance with type-safe tools

The `get_account_usage` tool monitors your active API limits and run counts. Pydantic AI parses this usage data into clean Python objects, making it easy to build automated alerts when you approach your monthly thresholds. You can pair this with `list_runs` to keep a clean, validated log of every execution. Your agent uses these typed records to decide whether to retry failed jobs.

Manage automation tasks without silent errors

The `create_task` tool builds new browser workflows programmatically from your agent. Pydantic AI validates the input parameters before sending them to the API, catching missing fields before they trigger a network request. Deleting old runs using `delete_run` also follows strict validation rules. This keeps your workspace clean while preventing accidental deletion of active automation tasks.

Setup guide

Set up Browserbear 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": {
        "browserbear-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Initialize the `MCPToolset` with your Vinkius HTTP endpoint URL. Pass this toolset directly into the `toolsets` argument of your Pydantic AI `Agent` using the MCP protocol.

The framework raises a validation error immediately, stopping execution before the bad data propagates. This guarantees that your agent only works with clean, typed outputs.

Yes, you can connect using either Streamable HTTP or SSE transports. The Vinkius gateway manages the transport layer so your Pydantic AI agent gets a consistent MCP connection.

Yes, Pydantic AI is completely model-agnostic. You can run local models via Ollama and still use the type-safe Browserbear tools.

The framework validates inputs locally before sending them through the Vinkius secure zero-trust proxy. Your session cookies, passwords, and task configurations are never stored in plaintext on the client side.

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