How to Use the GrowthBook MCP in Pydantic AI

Q: How do I set up the GrowthBook integration in Pydantic AI?

Install the required package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class pointing to your Vinkius HTTP URL, and pass it to the Agent constructor via the toolsets argument.

Q: What happens if I try to update a project that does not exist?

The updateproject tool will return an error from the GrowthBook API. The framework parses this error, allowing your agent to catch the exception and log the failure.

Type-safe feature flag management using the GrowthBook MCP Server with 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 GrowthBook MCP to Pydantic AI

Create your Vinkius account to connect GrowthBook 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 GrowthBook with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe flag creation via MCP Server

The `create_feature` tool builds new flags using strict schemas to prevent invalid configurations from reaching production. Your agent defines the flag properties, and Pydantic AI validates the structure before sending the API request. Running this MCP Server ensures that any response from the API matches your Python models. If GrowthBook returns an unexpected field, the framework fails loudly, stopping bad data from breaking your application.

Strict environment updates

The `update_environment` tool modifies environment-specific rules and targeting configurations. Your agent uses this to adjust rollout percentages or targeting conditions safely. Pydantic AI enforces type safety on these environment payloads at runtime. This prevents common mistakes like passing a string where a boolean or number is expected, protecting your production environments from configuration errors.

Project hierarchy validation

The `get_project` and `list_projects` tools fetch your organizational structure to ensure flags are created in the correct context. Your agent inspects these project details to maintain consistent naming conventions. Because this setup runs on a model-agnostic framework, you can use any LLM to organize your projects. Pydantic AI guarantees that the returned project lists always parse correctly, regardless of the underlying model's output formatting.

Setup guide

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

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

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

Install the required package using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class pointing to your Vinkius HTTP URL, and pass it to the `Agent` constructor via the `toolsets` argument.

If the server returns data that violates your schemas, Pydantic AI raises a validation error immediately. This prevents your agent from operating on corrupted or incomplete feature flag data.

Yes, this integration is completely model-agnostic. You can connect your agent to Ollama, OpenAI, or Anthropic while using the same toolset to manage your feature flags.

The `update_project` tool will return an error from the GrowthBook API. The framework parses this error, allowing your agent to catch the exception and log the failure.

Your API keys and flag states are secured through end-to-end transport encryption. Vinkius executes the server in a zero-trust sandbox, ensuring your credentials are never exposed to the LLM or stored on persistent disks.

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