How to Use the Olostep MCP in Pydantic AI

Q: How do I configure Olostep within a Pydantic AI agent?

Install the library with pip install "pydantic-ai-slimmcp". Then, instantiate MCPToolset pointing to your Vinkius HTTP endpoint and register the MCP server in your agent's toolsets list.

Q: Can Pydantic AI validate the output of an Olostep scrape?

Yes. When the agent calls scrapeurl, the returned HTML or markdown is passed directly into your Pydantic model for strict runtime type validation.

Q: Does the Olostep integration support asynchronous batching in Pydantic AI?

Yes. Your agent can trigger asynchronous batches using createbatch and poll getbatchresults to safely process large volumes of web data.

Q: Is the MCPServerHTTP class still used for connection?

No, MCPServerHTTP is deprecated. You should use the unified MCPToolset class to connect to your externally running Vinkius MCP server.

Extract structured web data directly into validated Python types using Pydantic AI with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Olostep MCP to Pydantic AI

Create your Vinkius account to connect Olostep to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Olostep with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe web scraping with Pydantic AI

If you need to guarantee that scraped web data strictly matches your internal database schemas, Pydantic AI is the tool for the job. Your agent can call `scrape_url` to pull down clean markdown, which is then instantly validated against your Pydantic models at runtime. This setup prevents silent failures. If a target website changes its layout and the returned data is malformed, your application fails loudly with a validation error rather than corrupting your database.

Validated bulk operations via MCP Server

For asynchronous operations, your agent can call `create_batch` to submit a list of target websites for background scraping. The status of these jobs is checked using `get_batch` until they are ready. Once complete, your agent pulls the raw text using `get_batch_results` and validates the entire payload against your predefined schema. This ensures that even bulk, multi-page data extractions maintain strict structural integrity.

Self-healing scraper selection

Your agent can dynamically inspect available scraping agents using `list_agents` and retrieve specific configurations via `get_agent`. This allows your agent to choose the correct scraping profile based on the target domain's complexity. To keep your operations reliable, the agent can run `check_olostep_status` and `get_usage` to verify API availability and budget before initiating a run. This keeps your runtime environment predictable and prevents unexpected API errors.

Setup guide

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

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

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

Install the library with `pip install "pydantic-ai-slim[mcp]"`. Then, instantiate `MCPToolset` pointing to your Vinkius HTTP endpoint and register the MCP server in your agent's toolsets list.

Yes. When the agent calls `scrape_url`, the returned HTML or markdown is passed directly into your Pydantic model for strict runtime type validation.

Yes. Your agent can trigger asynchronous batches using `create_batch` and poll `get_batch_results` to safely process large volumes of web data.

No, `MCPServerHTTP` is deprecated. You should use the unified `MCPToolset` class to connect to your externally running Vinkius MCP server.

All target URLs and scraped HTML content are processed in zero-trust, ephemeral V8 isolates on Vinkius. Your data is strictly isolated in transit and wiped immediately after the scraping transaction 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