How to Use the ConfigCat MCP in Pydantic AI

Validate ConfigCat flag data in Pydantic AI. Ensure your agent logic stays type-safe with 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 ConfigCat MCP to Pydantic AI

Create your Vinkius account to connect ConfigCat 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 ConfigCat with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate flag values in Pydantic AI

Every response from `get_setting_value` gets checked against your models. If the server returns bad data, the agent stops immediately. This prevents silent failures in your production code. You get full confidence that your flag states are valid.

Deploy configurations with the MCP Server

Use `create_config` to define new products. Your agent uses `list_configs` to audit your existing setup for compliance. This gives you a typed audit trail for your infrastructure. You know exactly what configurations exist at all times.

Automate feature lifecycle in Pydantic AI

Your agent removes old flags with `delete_setting` to reduce technical debt. It creates new ones via `create_setting` when you deploy features. This keeps your configuration clean and manageable. You rely on the agent to prune unused flags automatically.

Setup guide

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

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

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

You use the MCPToolset class to load the server. Add the toolset to your Agent instance to start calling flag functions.

Yes. Every tool call is validated against a schema. If the response doesn't match, the agent throws an error instead of continuing.

You can. The toolset supports both Streamable HTTP and SSE for external server connections.

Pydantic AI catches the connection error. Your agent can then decide to retry or fail gracefully based on your defined logic.

The server only processes your flag keys and environment values. We don't store your logs, and the connection is secured via your Vinkius token.

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

Mastra AI sdk-typescript

Start using the ConfigCat MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started