How to Use the Moloco MCP in Pydantic AI

Q: Can Pydantic AI handle Moloco campaign lists safely?

Yes. The listcampaigns tool returns a structured list that your agent validates. This prevents errors when looping through large account structures.

Type-safe Moloco management with Pydantic AI. No more runtime surprises when your agent talks to your ad accounts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moloco MCP to Pydantic AI

Create your Vinkius account to connect Moloco 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 Moloco with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type-safe Moloco tools

Every tool like `get_analytics_report` returns data validated against your Pydantic models. If the Moloco API changes, your agent crashes before it acts on bad data. This prevents the common issue of silent failures in ad ops. You get a clear, validated view of your campaigns every time.

Reliable campaign status updates

Your agent uses `update_campaign_status` with strictly enforced input schemas. You define the allowed status changes in your Pydantic models. This ensures your agent never sends invalid configurations to Moloco. It acts as a safety layer for your programmatic advertising.

Conversion data integrity

When your agent calls `list_conversions`, the response is verified against your schema. This ensures you are reading accurate conversion counts. This removes the risk of hallucinated fields or malformed data. Your agent makes decisions based on facts, not garbage data.

Setup guide

Set up Moloco 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": {
        "moloco-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Every response from the Moloco MCP server is validated against your Pydantic models. If the server returns something unexpected, the agent raises a validation error immediately.

Yes. The `list_campaigns` tool returns a structured list that your agent validates. This prevents errors when looping through large account structures.

You instantiate the MCPToolset with the server URL. Pydantic AI then registers the Moloco tools, ready for your agent to use.

The connection is local to your environment. The server validates incoming and outgoing data, ensuring no unverified information reaches your agent logic.

Your ad account identifiers and performance metrics are processed strictly within your runtime. The system discards data after the agent finishes 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