How to Use the Apify MCP in Pydantic AI

Q: How do I set up the Apify MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass the toolset object into the toolsets list when defining your Pydantic AI Agent to expose all scraping capabilities.

Q: How do I handle async scraping runs in Pydantic AI?

Have your agent call runactor to start the scraper asynchronously, which returns a run ID. Your agent can then use getrun to check the status periodically without blocking your main application loop.

Q: Can my agent check my Apify usage limits?

Yes, the getaccountlimits tool lets your agent query your current compute unit usage and account limits. This allows you to build safety checks that prevent your agent from launching expensive scrapers if your budget is spent.

Q: How does Pydantic AI secure my scraped Apify data?

All dataset items and key-value payloads fetched via getdatasetitems are processed directly within your local Python runtime. Vinkius executes these MCP calls using secure, ephemeral V8 isolates, ensuring your scraped web data is never stored, logged, or exposed to external third parties.

Type-safe web scraping with Pydantic AI. Validate raw Apify scraped datasets against python schemas at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apify MCP to Pydantic AI

Create your Vinkius account to connect Apify 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 Apify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe web scraping using Pydantic AI

This MCP Server exposes `get_dataset_items` to bring structure to web scraping by validating returned JSON directly against your Pydantic schemas at runtime. When your agent calls the tool, the returned JSON is validated directly against your Pydantic schemas. If a scraper returns unexpected fields or malformed data, your agent catches the validation error instantly instead of failing silently. This guarantees that only clean, structured web data enters your production database.

Manage scraper execution and runtime states

The `run_actor` and `run_actor_sync` tools let your agents start scraping jobs with strict input validation. Your agent can monitor active jobs using `get_run` and fetch run metadata that conforms to your strictly typed Python classes. If a scraper runs too long or hits an error, your agent can call `abort_run` to terminate the process. This keeps your runtime environment predictable and prevents runaway API costs from unmonitored scraping tasks.

Inspect scraper webhooks and key-value stores

The `list_webhooks` and `get_key_value_store` tools let your agent manage event-driven scraping workflows. Your agent can read raw text, HTML, or screenshots from the key-value store and validate the payloads before processing. This setup is ideal for complex scraping tasks where you need to check screenshots of failed runs. By using Pydantic AI, you ensure that every file path and webhook URL is fully validated before your agent acts on it.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass the toolset object into the `toolsets` list when defining your Pydantic AI `Agent` to expose all scraping capabilities.

Yes, you can define a Pydantic model for your expected scraper output and use it to validate the JSON returned by `get_dataset_items`. If the scraped data doesn't match your schema, Pydantic AI raises a validation error immediately.

Have your agent call `run_actor` to start the scraper asynchronously, which returns a run ID. Your agent can then use `get_run` to check the status periodically without blocking your main application loop.

Yes, the `get_account_limits` tool lets your agent query your current compute unit usage and account limits. This allows you to build safety checks that prevent your agent from launching expensive scrapers if your budget is spent.

All dataset items and key-value payloads fetched via `get_dataset_items` are processed directly within your local Python runtime. Vinkius executes these MCP calls using secure, ephemeral V8 isolates, ensuring your scraped web data is never stored, logged, or exposed to external third parties.

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