How to Use the NinjaCat MCP in Pydantic AI

Q: Can I use my Pydantic AI agent to create new advertisers in NinjaCat?

No. This toolset is strictly for reading data. You can getadvertiser details, but you can't create or update them. The focus is on safe, validated data retrieval.

Q: Does Pydantic AI work with any LLM for this NinjaCat MCP toolset?

Yes, it's model-agnostic. You can connect the NinjaCat MCPToolset to an agent powered by OpenAI, Gemini, Claude, or even a local model running on your machine. The validation logic is independent of the LLM.

Add type-safe, validated access to your NinjaCat data in any Python application with Pydantic AI. No more 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 NinjaCat MCP to Pydantic AI

Create your Vinkius account to connect NinjaCat 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 NinjaCat with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Reliable, Validated Report Data

This toolset lets your agent fetch marketing report information from NinjaCat. When your agent calls `list_reports`, the response isn't just a blob of JSON. Pydantic AI automatically validates it against a strict schema, ensuring every field is the right type. If NinjaCat's API ever sends back something unexpected—a missing field, a string instead of a number—your agent will fail with a clear `ValidationError`. This prevents corrupted data from silently flowing through your system. You trade silent failures for loud, obvious correctness.

Build Trustworthy Internal Tools

Use these tools to build internal dashboards or alerting systems that you can actually trust. Your agent can use `list_data_sources` and `list_data_accounts` to periodically check that all your ad accounts are properly connected in NinjaCat. If the validation passes, you know the data is sound. Since Pydantic AI is model-agnostic, you can use these tools with any LLM—OpenAI, Anthropic, a local model, whatever. The validation happens in your Python code, independent of the model, giving you a consistent layer of data integrity.

A Predictable MCP Server for NinjaCat

The workflow is straightforward and predictable. The agent calls `list_advertisers` to find an account, `list_reports` to find a report for that account, and `get_report_download_url` to get the link. At each step, Pydantic AI is checking the data structure. This MCP Server is read-only, which fits perfectly with a safety-first mindset. Your agent can't accidentally modify a campaign or delete a report. It's designed for safe, reliable data retrieval, and Pydantic AI adds another layer of assurance on top.

Setup guide

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

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

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

When your agent gets a response from a tool on this MCP server like `list_reports`, Pydantic AI automatically tries to parse it into a Pydantic model. If the data doesn't match the expected structure and types, it raises a `ValidationError` immediately.

No. This toolset is strictly for reading data. You can `get_advertiser` details, but you can't create or update them. The focus is on safe, validated data retrieval.

The main benefit is data integrity. You can be certain that the marketing data your agent is working with matches the exact schema you defined, which eliminates a whole class of bugs related to unexpected API changes.

Yes, it's model-agnostic. You can connect the NinjaCat `MCPToolset` to an agent powered by OpenAI, Gemini, Claude, or even a local model running on your machine. The validation logic is independent of the LLM.

Vinkius processes each request for report metadata or campaign info in a fresh, ephemeral sandbox that is destroyed after use. Your Pydantic AI agent authenticates with a single token, so your actual NinjaCat keys are never exposed. The data itself only exists in-memory during the request.

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