How to Use the LinkedIn Ads MCP in Pydantic AI

Q: Can I use Pydantic AI to safely toggle LinkedIn Ads campaign statuses?

Yes, you can configure strict input schemas for enablecampaign and pausecampaign. This ensures the agent only sends valid campaign IDs and correct boolean states, preventing runtime execution failures.

Deploy type-safe B2B marketing agents that validate LinkedIn Ads campaign data at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkedIn Ads MCP to Pydantic AI

Create your Vinkius account to connect LinkedIn Ads 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 LinkedIn Ads with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation for LinkedIn Ads data

The LinkedIn Ads MCP Server feeds structured data directly into Pydantic AI's strict runtime validation engine. When your agent calls `get_account_analytics` or `get_campaign_analytics`, every returned metric is instantly validated against Pydantic models to catch API drift or unexpected null values before they corrupt your data pipelines. If the LinkedIn API returns an unexpected data type, your Python application fails loudly and immediately. This behavior prevents your Pydantic AI agent from making critical LinkedIn budget decisions based on malformed or hallucinated performance metrics.

Type-safe campaign control and state management

The LinkedIn Ads MCP Server ensures that structural changes to your campaigns are executed with absolute type safety. Tools like `enable_campaign` and `pause_campaign` require strict, validated inputs that Pydantic AI enforces at the schema level before the request ever leaves your application. Your Pydantic AI agent cannot execute a LinkedIn status change with malformed campaign IDs or invalid parameter types. This constraint guarantees that your automated budget adjustments are structurally sound and conform exactly to LinkedIn's API requirements.

Model-agnostic MCP Server integration for B2B marketers

The LinkedIn Ads MCP Server integrates directly with Pydantic AI's model-agnostic architecture. You can swap your underlying LLM from OpenAI to Anthropic or a local model without changing a single line of your tool execution logic for `list_campaigns` or `list_creatives`. Bottom line: this flexibility allows you to optimize your LinkedIn automation for cost or speed depending on the task. Use a smaller, faster model to poll `get_account_info` and switch to a highly capable reasoning model only when executing complex budget reallocations.

Setup guide

Set up LinkedIn 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": {
        "linkedin-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 LinkedIn Ads tools.",
)

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

Use the unified toolset class pointing to your Vinkius HTTP URL. Pass this toolset directly into the toolsets parameter of your agent constructor to expose tools like `list_campaigns` to your model.

The framework validates all incoming data, such as responses from `get_campaign_analytics`, against strict schemas. If the API returns unexpected fields, the runtime throws a validation error instead of passing bad data to your agent.

Yes, you can configure strict input schemas for `enable_campaign` and `pause_campaign`. This ensures the agent only sends valid campaign IDs and correct boolean states, preventing runtime execution failures.

No, Pydantic AI manages the connection internally when you use the unified toolset class. It handles the underlying streamable HTTP or SSE transport protocol automatically.

Yes, your campaign metrics, creatives, and account info pass directly through the Vinkius zero-trust sandbox to your local Pydantic AI runtime. The data is validated locally in your memory space, ensuring your marketing performance metrics are never stored or cached externally.

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