How to Use the Microsoft Ads MCP in Pydantic AI

Q: What happens if Microsoft Ads returns malformed budget data to Pydantic AI?

If listmsbudgets returns data that violates your Pydantic models, the framework raises a validation error. This prevents your agent from acting on corrupted budget numbers.

Q: Can I use Pydantic AI to validate Microsoft Ads targeting settings?

Yes. When your agent calls listmstargetingsettings, the framework parses the response against your defined Pydantic schemas, ensuring all location and device fields are typed correctly.

Q: How does the server protect my Microsoft Ads account credentials?

Your credentials, used to authenticate getmsaccountinfo, are encrypted at rest and injected only during runtime. The Vinkius sandbox prevents any persistent storage or leakage of your developer tokens.

Write type-safe Python agents that validate Microsoft Ads schemas at runtime with Pydantic AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Microsoft Ads MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Campaign Discovery with Pydantic AI

The `list_ms_campaigns` tool returns structured Microsoft Ads data that Pydantic AI validates against strict Python models at runtime. If the API structure changes, your agent fails immediately instead of processing corrupt data. You use `search_ms_campaigns` to find specific ad runs with complete type safety. This guarantees that fields like budget limits and status codes match your application's expected types before any logic runs.

Budget Validation via Pydantic AI

This MCP Server uses `list_ms_budgets` to pull shared budget details directly into your type-safe agent. The framework ensures that decimal values and currency codes conform exactly to your Pydantic schemas. By calling `get_ms_account_info`, your agent verifies account IDs and balances. This prevents silent failures where an empty or malformed API response could lead to wrong budget calculations.

Ad Group and Keyword Audits

Use `list_ms_keywords` to extract keyword lists with strict type verification. Pydantic AI parses the API payload, ensuring every keyword string and match type matches your data models. The agent calls `get_ms_ad_group_details` via this MCP integration to verify targeting parameters. If the API returns unexpected values, the framework raises a validation error, protecting your downstream application from bad data.

Setup guide

Set up Microsoft 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": {
        "microsoft-ads-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You import MCPToolset with your HTTP endpoint and pass it to the Agent constructor. The framework auto-discovers tools like list_ms_campaigns and builds runtime validation schemas for them.

If list_ms_budgets returns data that violates your Pydantic models, the framework raises a validation error. This prevents your agent from acting on corrupted budget numbers.

Yes. When your agent calls list_ms_targeting_settings, the framework parses the response against your defined Pydantic schemas, ensuring all location and device fields are typed correctly.

Yes. Pydantic AI handles async tool calls natively, allowing you to fetch list_ms_ads and list_ms_keywords concurrently.

Your credentials, used to authenticate get_ms_account_info, are encrypted at rest and injected only during runtime. The Vinkius sandbox prevents any persistent storage or leakage of your developer tokens.

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