How to Use the Bright Data MCP in Pydantic AI

Q: Where are my Bright Data zone passwords stored?

The server retrieves them via getzonepasswords on demand. These are never stored in your agent code or local persistence.

Build type-safe scraping agents using Pydantic AI and this MCP Server to ensure your web data is always valid.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bright Data MCP to Pydantic AI

Create your Vinkius account to connect Bright Data 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 Bright Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate scraping results in Pydantic AI

Use `get_dataset_snapshot` to feed raw data into your Pydantic AI models. If the schema doesn't match your expectations, the agent throws a validation error immediately. This prevents bad data from hitting your downstream services. You catch issues at the boundary instead of finding them later.

Monitor scraping state with Pydantic AI

Call `list_datasets` and `get_dataset_progress` to keep your agent informed. The server ensures the tool responses follow the types you defined. Your agent logic stays clean because it only deals with validated objects. It knows exactly what to expect from every tool call.

Automate proxy requests using Pydantic AI

Use `send_request` to hit the Unlocker API. Your agent constructs the request, and the tool returns a strictly typed result that Pydantic AI checks for correctness. This prevents the agent from hallucinating fields in the API response. You get the data you requested or an explicit error.

Setup guide

Set up Bright Data 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": {
        "bright-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Yes, every tool response is verified against your Pydantic models. If the server output deviates, your agent stops the task.

Initialize the MCPToolset with the Vinkius endpoint. Add it to your agent's toolsets list to start calling the tools.

Since this is an MCP Server, it works with any model supported by Pydantic AI. The model agnostic nature keeps your setup flexible.

The server retrieves them via `get_zone_passwords` on demand. These are never stored in your agent code or local persistence.

The server ensures that only your authenticated requests access your specific datasets. Your scraping history and snapshot files remain isolated in the Vinkius sandbox.

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