Do I need the ParseHub Desktop tool running to use this?

No. This integration operates completely natively via ParseHub's Cloud API endpoints. You only need the desktop app to build the templates originally. All executions mapped here happen on their cloud scaling servers.

Can I provide a different Start URL when running a project?

Yes. The `run_project_with_url` command allows you to explicitly provide a `start_url` query property. This instructs the ParseHub crawler to ignore its project-saved URL and begin parsing the newly mapped domain using the same semantic template.

Is the downloaded data returned in JSON or raw HTML?

The payload fetched by `get_run_data` is exported entirely as structured, pre-parsed JSON mirroring the exact template node selections defined in your project architecture.

ParseHub MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: ParseHub
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ParseHub through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to ParseHub "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in ParseHub?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About ParseHub MCP Server

Bring ParseHub Cloud Scraping directly into your AI workflows. Manage pre-configured web scraping targets natively and orchestrate complex headless browser automation directly from chat. Dispatch run jobs on command, query execution status limits, and extract final parsed payloads securely.

Pydantic AI validates every ParseHub tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Navigation — Inspect and list configured ParseHub projects, determining start URLs, templates, and total crawler pages attached
Execution Dispatch — Command remote servers to trigger specific headless data extraction jobs run_project optionally overriding starting URLs natively
Observability Tracing — Monitor exactly where a Run object is (queued, initialized, running, complete) without checking the desktop app
Payload Extraction — Pull down structured arrays containing the scraped payloads securely via get_run_data matching explicit datasets

The ParseHub MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect ParseHub to Pydantic AI via MCP

Follow these steps to integrate the ParseHub MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from ParseHub with type-safe schemas

Why Use Pydantic AI with the ParseHub MCP Server

Pydantic AI provides unique advantages when paired with ParseHub through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your ParseHub integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your ParseHub connection logic from agent behavior for testable, maintainable code

ParseHub + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the ParseHub MCP Server delivers measurable value.

Type-safe data pipelines: query ParseHub with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple ParseHub tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query ParseHub and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock ParseHub responses and write comprehensive agent tests

ParseHub MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect ParseHub to Pydantic AI via MCP:

cancel_run

If the run was already scraping pages, partial data may be available. Data from already-scraped pages is preserved and can be retrieved with get_run_data. Use this to stop long-running scrapes or free up queue slots. Cancel a queued or actively running ParseHub run

delete_run

Cannot be undone. Use this to clean up old runs and free up storage quota on your account. Permanently delete a ParseHub run and its extracted data

get_last_ready_data

Ideal for dashboards or integrations that always want the freshest available data without managing individual run tokens. Instantly get the latest completed data for a ParseHub project

get_project

The project_token can be found via list_projects or in the ParseHub desktop client settings tab. Get detailed configuration of a specific ParseHub project

get_run_data

Only works when the run status is "complete" and data_ready is true. The JSON structure mirrors the template selection configuration set up in the ParseHub desktop client. Download the raw JSON data extracted from a completed ParseHub run

get_run_details

Poll this endpoint to wait for a run to complete before fetching data. Check the status of a specific ParseHub run

list_projects

Each project includes a project_token (unique identifier), title, last_run timestamp, and template configuration. Use the project_token for all subsequent run management operations. List all ParseHub web scraping projects

list_runs

Useful for auditing or finding a specific completed run to fetch data from. Get the history of all runs for a ParseHub project

run_project

Returns a run_token for tracking progress. The run enters a queue and begins processing within seconds. Use get_run to monitor and get_run_data to retrieve results once complete. Start a new ParseHub scraping run for a project

run_project_with_url

Perfect for scraping different pages with the same template (e.g., different product categories). The template extraction rules still apply unchanged — only the starting page changes. Start a ParseHub run targeting a custom URL instead of the project default

Example Prompts for ParseHub in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with ParseHub immediately.

"Fetch the list of scrape projects I have on my ParseHub account."

"Start a new run for project 't9zx...' and check its status."

"Extract the finished data JSON payload from run ID 'run_k1l'."

Troubleshooting ParseHub MCP Server with Pydantic AI

Common issues when connecting ParseHub to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ParseHub + Pydantic AI FAQ

Common questions about integrating ParseHub MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your ParseHub MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.