How to Use the GrowingIO MCP in Pydantic AI

Build type-safe analytics agents using Pydantic AI to validate GrowingIO event data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrowingIO MCP to Pydantic AI

Create your Vinkius account to connect GrowingIO 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 GrowingIO with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe cohort analysis with Pydantic AI

Your Pydantic AI agent uses `get_segment_users` to perform type-safe cohort analysis without malformed GrowingIO API responses. By configuring this GrowingIO MCP Server, your Pydantic AI agent validates the returned user lists from `list_segments` against strict Python types. If the GrowingIO server returns unexpected fields, Pydantic AI catches the error immediately before execution. This prevents corrupted GrowingIO cohort data from polluting your downstream Pydantic AI pipelines.

Validate funnel metrics with this MCP Server

Your Pydantic AI agent calls `get_funnel` to validate GrowingIO conversion percentages and event counts. By calling `get_metrics` through a validated Pydantic AI toolset, you ensure that GrowingIO metrics match your exact schema definitions. Our Pydantic AI agent uses these strict types to build reliable GrowingIO dashboards. If a GrowingIO metric field is missing or formatted incorrectly, the Pydantic AI runtime fails loudly so you can fix the tracking setup.

Inspect project tracking schemas safely

Your Pydantic AI agent uses `list_variables` to check which custom GrowingIO properties are currently active. The agent checks `list_events` to audit your GrowingIO tracking plan, validating them against your internal Pydantic AI data schemas. It can then call `get_project_info` to verify that the GrowingIO SDK integration is running correctly. This automated GrowingIO auditing pipeline runs continuously inside your Pydantic AI application without manual oversight.

Setup guide

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

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

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

Instantiate the MCP Server toolset with your Vinkius GrowingIO URL, then pass it inside the `toolsets` list when initializing your Pydantic AI `Agent`.

Yes, Pydantic AI validates both the input parameters for tools like `get_event` and the JSON responses returned by the GrowingIO server.

The Pydantic AI framework raises a validation or network error immediately, preventing your agent from hallucinating GrowingIO metrics.

Yes, the GrowingIO toolset is model-agnostic, allowing you to use Pydantic AI with local or cloud models as long as they support tool calls.

Runtime validation in Pydantic AI ensures that only explicitly defined GrowingIO event and metric fields are processed, and the Vinkius MCP Server gateway uses zero-trust token authentication.

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