How to Use the Basis Technologies MCP in Pydantic AI

Q: How do I add Basis Technologies to a Pydantic AI agent?

Install pydantic-ai-slimmcp via pip. Create an MCPToolset with your Vinkius HTTP URL and pass it in the toolsets array when building your Agent.

Q: Does Pydantic AI validate Basis Technologies campaign data?

Every response from tools like getcampaign is checked against your defined Pydantic models. The framework catches missing fields or incorrect types immediately.

Connect Pydantic AI to Basis Technologies. Validate every DSP campaign and ad metric against strict schemas before your agent acts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basis Technologies MCP to Pydantic AI

Create your Vinkius account to connect Basis Technologies 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 Basis Technologies with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Basis Technologies Metrics

Retrieving programmatic spend requires `get_campaign_performance` and `get_tactic_performance`. Pydantic AI forces every JSON response from these endpoints into strict data models. If the DSP API returns a string instead of a float for spend, the agent fails loudly with a validation error. This prevents silent data corruption in your reporting pipelines. You configure the connection using `MCPToolset` with the Vinkius HTTP URL. The agent refuses to process hallucinated fields, ensuring your marketing dashboards only display real numbers.

Sync Campaigns via MCP Server

Pulling media plans involves `list_campaigns`, `get_campaign`, and `list_tactics`. The agent fetches the hierarchy and maps each line item to its parent. Because the framework is model-agnostic, you can run this extraction using OpenAI, Anthropic, or local LLMs. The unified toolset approach replaces the deprecated MCPServerHTTP class. You pass the toolset directly to the Agent constructor. Strict typing guarantees that flight dates and budget caps match your expected formats before any downstream logic executes.

Audit Clients and Ad Creatives

Inspecting an account starts with `list_clients` and `list_brands`. The agent groups the advertisers and then calls `list_ads` or `get_ad` to check the creative metadata. Runtime validation ensures that every brand ID matches the expected integer or UUID format. The server runs externally on Vinkius, handling the actual API requests. Your Python application remains lightweight and focused purely on logic. Just provide the endpoint token, and the framework handles the Streamable HTTP transport automatically.

Setup guide

Set up Basis Technologies 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": {
        "basis-technologies-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install pydantic-ai-slim[mcp] via pip. Create an MCPToolset with your Vinkius HTTP URL and pass it in the toolsets array when building your Agent.

Every response from tools like get_campaign is checked against your defined Pydantic models. The framework catches missing fields or incorrect types immediately.

The agent throws a strict validation error and stops execution. It will never silently pass malformed ad metrics or hallucinated campaign IDs into your application.

The framework is completely model-agnostic. You can connect local models to the server and have them analyze responses from list_tactics or list_ads.

Your campaign budgets and client lists remain secure. The Python agent only handles the endpoint token, while Vinkius executes the calls in an ephemeral sandbox.

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