How to Use the Pinterest Ads MCP in Pydantic AI

Q: Can I monitor Pinterest Ads performance with Pydantic AI?

You can. Use getadgroupanalytics to pull metrics. Your agent then validates these numbers against your defined performance thresholds.

Build type-safe Pinterest Ads workflows with Pydantic AI to ensure every campaign action is validated at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pinterest Ads MCP to Pydantic AI

Create your Vinkius account to connect Pinterest Ads to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pinterest Ads with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Campaign Control in Pydantic AI

Every tool call like `enable_campaign` is validated against strict schemas. If the API returns unexpected data, your agent catches the error before it propagates. This prevents silent failures. You get a reliable system that stops instantly if the data doesn't match your expected model.

Validated Analytics for Pydantic AI

Use `get_campaign_analytics` to pull data into your typed Pydantic models. Your agent ensures the output is correct before executing any strategy. It eliminates hallucinated fields. You trust the data because your agent refuses to act on malformed responses.

Structured Ad Inventory in Pydantic AI

Call `list_ads` to populate your agent's knowledge base with validated Pin data. It understands your creative assets through a strictly typed interface. This makes your logic predictable. Your agent knows exactly what it's working with every time.

Setup guide

Set up Pinterest Ads 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": {
        "pinterest-ads-1-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Pinterest Ads 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 Pinterest Ads. 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.