How to Use the Pinterest Ads MCP in OpenAI Agents SDK

Q: How does the Pinterest Ads MCP server integrate with OpenAI Agents SDK?

You pass the server URI to MCPServerStreamableHttp and register it in the mcpservers list of your OpenAI Agent. The OpenAI SDK auto-discovers all ten Pinterest tools, including listpinterestcampaigns, making them instantly callable by your agent.

Q: How do I handle rate limits when querying Pinterest Ads MCP Server with OpenAI Agents SDK?

Set cacheToolsList=True in your OpenAI Agent configuration to avoid redundant Pinterest tool discovery calls. Your OpenAI agent then queries listpinterestads and listpinterestpins using cached schemas, saving your Pinterest API quota.

Run secure, automated Pinterest Ads optimization pipelines using the OpenAI Agents SDK with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Pinterest Ads to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Verify ad budgets before execution with OpenAI Agents SDK

The `get_pinterest_campaign` tool feeds raw budget parameters directly into your OpenAI Agents SDK runtime. This prevents your OpenAI agent from making unauthorized Pinterest bidding changes. By using `list_pinterest_campaigns` alongside OpenAI's built-in guardrails, you block runaway Pinterest ad spend. Your OpenAI agent verifies the Pinterest campaign status and halts execution if the metrics don't align.

Track campaign performance without manual reports

The `get_pinterest_analytics` tool pulls raw Pinterest conversion metrics directly into your OpenAI tracing dashboard. You see every Pinterest ad tool call and data payload inside the OpenAI platform in real-time. Instead of exporting spreadsheets, your OpenAI agent uses `list_pinterest_ad_groups` to isolate underperforming Pinterest ad sets. OpenAI's SDK then routes this data to specialized OpenAI agents that swap out Pinterest assets.

Audit active keywords and boards automatically

The `list_pinterest_keywords` tool exposes active Pinterest search terms to your autonomous OpenAI agents. Your OpenAI agent identifies search queries on Pinterest that drain your budget without driving conversions. It cross-references these keywords with Pinterest asset lists from `list_pinterest_boards` using OpenAI's agent handoffs. You get clean, automated Pinterest keyword scrubbing inside your OpenAI workflow without custom integration code.

Setup guide

Set up Pinterest Ads MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Pinterest Ads tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Pinterest Ads tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Pinterest Ads tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Pinterest Ads Agent",
            instructions="You have access to Pinterest Ads tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Pinterest Ads 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 Pinterest Ads MCP in OpenAI Agents SDK

You pass the server URI to `MCPServerStreamableHttp` and register it in the `mcp_servers` list of your OpenAI Agent. The OpenAI SDK auto-discovers all ten Pinterest tools, including `list_pinterest_campaigns`, making them instantly callable by your agent.

Yes, you restrict access to Pinterest tools by configuring the tools list during OpenAI agent initialization. This keeps sensitive operations like modifying Pinterest budgets restricted while allowing read-only tools like `get_pinterest_analytics` to run inside the OpenAI SDK.

Set `cacheToolsList=True` in your OpenAI Agent configuration to avoid redundant Pinterest tool discovery calls. Your OpenAI agent then queries `list_pinterest_ads` and `list_pinterest_pins` using cached schemas, saving your Pinterest API quota.

Yes, you can build multi-agent architectures where one OpenAI agent analyzes Pinterest performance via `get_pinterest_analytics`. That agent then hands off the raw metrics to a second OpenAI agent that adjusts Pinterest targeting using `list_pinterest_audiences`.

Your Pinterest API tokens and campaign analytics never touch third-party databases outside of your OpenAI runtime. The Vinkius connection runs through an ephemeral V8 sandbox that processes your Pinterest `list_pinterest_catalogs` queries and discards the session data immediately after your OpenAI agent completes its task.

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