How to Use the Countly MCP in Pydantic AI

Q: Does Pydantic AI enforce schemas for Countly tools?

It does. The MCPToolset validates all inputs and outputs against your models. If the server returns something unexpected, you get a validation error instead of a crash.

Q: How do I link Countly to my Pydantic AI agent?

You instantiate the MCPToolset with your server URL and add it to your agent. The setup is designed for strict, type-safe Python environments.

Q: Does Pydantic AI support drill queries for Countly?

The readdrill tool is ready for use. Your agent sends the request, and the result is mapped to your model, providing a safe way to analyze your data.

Type-safe Countly analytics integration for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Countly MCP to Pydantic AI

Create your Vinkius account to connect Countly 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 Countly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI agents managing Countly sessions

Every call to `begin_session`, `end_session`, or `update_session` undergoes strict validation. Your agent won't send malformed data because the schema is checked against your models at runtime. This approach prevents silent failures when your agent interacts with session states. If an API response looks wrong, your code catches it immediately.

Reading Countly data with Pydantic AI

Pull standard data points using `read_metrics` and be confident in the structure of the response. The tool returns data that your agent can safely use for its next step. When you need granular details, `read_events` delivers specific logs. Your agent receives typed objects, making your logic cleaner and more predictable.

Complex Countly queries in Pydantic AI

Perform deep segmentation using `read_drill`. Your agent sends the query and receives a validated result, ensuring no hallucinated fields leak into your analysis. Logging actions is handled by `record_events`. Because you use Pydantic AI, you know exactly what data format is expected before the request is even sent.

Setup guide

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

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

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

It does. The `MCPToolset` validates all inputs and outputs against your models. If the server returns something unexpected, you get a validation error instead of a crash.

You instantiate the `MCPToolset` with your server URL and add it to your agent. The setup is designed for strict, type-safe Python environments.

The server enforces authentication on every connection. Your behavioral logs are handled in memory and validated by the schema, so no corrupted data enters your system.

Yes, it's a standard tool in the set. Your agent updates user attributes, and the Pydantic model ensures the payload is perfectly formatted.

The `read_drill` tool is ready for use. Your agent sends the request, and the result is mapped to your model, providing a safe way to analyze your data.

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