How to Use the Cradl AI MCP in Pydantic AI

Q: How do I handle model searches in Pydantic AI?

Use searchmodelsbyname. The results come back as structured data that your agent can immediately parse and validate.

Use Cradl AI with Pydantic AI for type-safe document extraction that fails loudly on bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cradl AI MCP to Pydantic AI

Create your Vinkius account to connect Cradl AI 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 Cradl AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate extraction results in Pydantic AI

Your agent uses `extract_data_from_url` to pull data. Pydantic AI automatically checks the output against your models at runtime. If the data structure is wrong, the agent stops immediately. This prevents silent corruption in your document processing chain.

Check task status in Pydantic AI

Call `list_processing_tasks` to view the status of your document tasks. Your agent confirms if a task is PENDING, COMPLETED, or FAILED. `get_task_status` returns the key-value pairs you need. Pydantic AI enforces the types for every field.

Manage models in Pydantic AI

Use `list_extraction_models` to pull model metadata. Your agent validates the available versions and statuses before running a job. `get_model_details` provides the schema definitions your agent needs. You ensure every extraction runs against a valid model configuration.

Setup guide

Set up Cradl AI 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": {
        "cradl-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the pydantic-ai-slim package. Define an MCPToolset using your server URL and pass it to your agent during setup to enable type-safe tool calls.

Yes. Every response is checked against your Pydantic models. If the API returns unexpected data, the agent triggers a validation error to catch the issue instantly.

The server supports both Streamable HTTP and SSE. You can choose the transport that matches your Pydantic AI implementation needs.

Use `search_models_by_name`. The results come back as structured data that your agent can immediately parse and validate.

We keep your document content and extracted fields separate from other users. Our security model uses individual tokens for every session to ensure your data stays private.

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