How to Use the Delta Projects MCP in Pydantic AI

Q: How do I initialize Delta Projects in Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset with your Vinkius HTTP URL, and add it to the toolsets list when defining your Agent. Do not use the deprecated MCPServerHTTP class.

Build type-safe marketing agents that validate every Delta Projects API response 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 Delta Projects MCP to Pydantic AI

Create your Vinkius account to connect Delta Projects 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 Delta Projects with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Delta Projects MCP Server Validation

Silent data corruption destroys reporting pipelines. When your Pydantic AI agent calls `list_ad_campaigns`, the framework validates the incoming JSON against your predefined models. If the API returns a string where an integer should be, the agent fails loudly. This strictness matters when handling budgets. You can use `get_campaign_performance` knowing that the spend metrics match the exact schema you expect. You never pass hallucinated numbers to your downstream analytics tools.

Model-Agnostic Ad Reporting

You are not locked into a single LLM provider. Whether you use Anthropic or local models, the agent pulls granular data via `get_custom_ad_report`. It structures the dimensions and metrics perfectly every time. The agent can iterate through your client list using `list_managed_advertisers` and generate identical, type-checked reports for each one. The unified `MCPToolset` setup ensures the MCP connection remains stable regardless of which model powers the reasoning.

Guaranteed Asset Verification

Auditing creatives requires exact metadata. Your agent queries `list_ad_creatives` to pull banner and video specs. Because Pydantic checks the response at runtime, you know the format and file size fields actually exist before your code tries to parse them. The same logic applies to targeting. The agent fetches first-party lists via `list_target_audiences` and checks them against `list_media_placements`. If any placement data is missing expected keys, you get a validation error immediately instead of a broken campaign later.

Setup guide

Set up Delta Projects 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": {
        "delta-projects-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` with your Vinkius HTTP URL, and add it to the `toolsets` list when defining your Agent. Do not use the deprecated MCPServerHTTP class.

It catches everything. If the server returns unexpected JSON for a campaign search, Pydantic throws a validation error instantly. Your agent will never confidently present malformed data.

Yes. The framework is completely model-agnostic. As long as your local model supports tool calling, it can interact with the marketing endpoints just like a commercial API would.

We recommend Streamable HTTP for production workloads. The MCP toolset handles the connection automatically, keeping your agent focused on data extraction rather than networking issues.

Your data routes through our ephemeral V8 Isolate Sandbox. The moment Pydantic AI finishes validating your campaign metrics, the sandbox terminates. We maintain a strict zero-trust architecture with zero persistent storage.

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