Crawlbase MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Crawlbase through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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 Crawlbase "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in Crawlbase?"
)
print(result.data)
asyncio.run(main())
* 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 Crawlbase MCP Server
Connect your Crawlbase (formerly ProxyCrawl) account to any AI agent and take full control of your web scraping and anonymous crawling workflows through natural conversation.
Pydantic AI validates every Crawlbase tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the 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
- Standard Scraper — Identify bounded routing spaces inside the headless engine to extract explicitly attached HTML content via datacenter proxies
- JS Rendering — Discover disconnected physical limits tracking exactly what JS-rendered frames expose to extract exact single-page UI bounds
- Structured JSON Extraction — Analyzes specific global bounds driving auto-extraction pipelines to force raw HTTP outputs into structured JSON format strictly
- Screenshot Capture — Dispatch automated validation checks to generate valid proxy endpoints returning configured Crawlbase screenshot URLs
- Specialized Scraping — Leverage dedicated algorithms for Amazon products, LinkedIn profiles, Facebook pages, and Twitter (X) graph profiles natively
- Search Engine Discovery — Explain explicitly mapped proxy lists targeting Google domains to parse SERP limits and bypass CAPTCHAs limitlessly
- Custom Proxy Management — Provision highly-available request payloads generating custom proxies with specific headers and crawling logic
The Crawlbase 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 Crawlbase to Pydantic AI via MCP
Follow these steps to integrate the Crawlbase 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 Crawlbase with type-safe schemas
Why Use Pydantic AI with the Crawlbase MCP Server
Pydantic AI provides unique advantages when paired with Crawlbase 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 Crawlbase integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Crawlbase connection logic from agent behavior for testable, maintainable code
Crawlbase + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Crawlbase MCP Server delivers measurable value.
Type-safe data pipelines: query Crawlbase with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Crawlbase tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Crawlbase and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Crawlbase responses and write comprehensive agent tests
Crawlbase MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect Crawlbase to Pydantic AI via MCP:
custom_scrape
Provision a highly-available Request Payload generating Custom proxies
get_screenshot_link
Dispatch an automated validation check routing explicit Web Snapshot domains
scrape_amazon
Inspect deep internal arrays mitigating specific E-Commerce constraints
scrape_facebook
Enumerate explicitly attached structured rules exporting active Social Pages
scrape_google_serp
Identify precise active arrays spanning rented Context domains for Search
scrape_html
crawlbase.com` datacenter proxies. Identify bounded routing spaces inside the Headless Crawlbase Engine
scrape_js_rendered
Retrieve explicit Cloud logging tracing explicit Payload IDs limitlessly
scrape_json_format
Perform structural extraction of properties driving active Fields
scrape_linkedin
Retrieve the exact structural matching verifying Blueprint constraints
scrape_twitter
Fetch elaborate explicit mapped limits via Crawlbase X extraction
Example Prompts for Crawlbase in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Crawlbase immediately.
"Scrape the price and features from this Amazon product: [Amazon URL]"
"Get Google search results for 'best machine learning platforms 2024'"
"Take a screenshot of https://example.com"
Troubleshooting Crawlbase MCP Server with Pydantic AI
Common issues when connecting Crawlbase to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiCrawlbase + Pydantic AI FAQ
Common questions about integrating Crawlbase MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Connect Crawlbase with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Crawlbase to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.