How to Use the Countly MCP in OpenAI Agents SDK

Q: How do I connect Countly to my OpenAI Agents SDK project?

You pass the server URL to the MCPServerStreamableHttp constructor. Once you add it to your agent's list, the tools are discovered automatically. It's a standard setup for your Python workflow.

Q: Can my OpenAI Agents SDK agent update Countly user profiles?

Yes, it uses the updateuserdetails tool. Your code sends the payload, and the agent updates the record in real-time. It keeps your analytics database accurate.

Q: Does the server support custom events for OpenAI Agents SDK?

It does. You can use the recordevents tool to push custom actions into your analytics stream. The agent handles the data formatting before sending it over.

Q: How does OpenAI Agents SDK handle Countly drill queries?

The readdrill tool runs your query on the server side. You get a structured response that your agent can process or summarize. It keeps the heavy lifting off your local machine.

Track user behavior and push custom events using Countly directly from your OpenAI Agents SDK production pipeline.

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 OpenAI Agents SDK

Create your Vinkius account to connect Countly to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Countly sessions inside OpenAI Agents SDK

Control user life cycles by firing `begin_session` and `end_session` calls during agent execution. You can keep session data fresh by using `update_session` when your agent detects continued user activity. Your production agent monitors these states without manual intervention. It triggers `update_user_details` to sync backend profiles while staying inside your defined safety constraints.

Query Countly analytics with OpenAI Agents SDK

Fetch raw event logs using `read_events` to feed your agent context about what users are actually doing. This MCP Server lets your logic parse specific user actions immediately after they occur. Standard metrics like active user counts or geographic distribution arrive via `read_metrics`. You get the data you need without leaving your Python environment.

Deep behavioral analysis in OpenAI Agents SDK

Run `read_drill` to execute complex queries against your Countly data sets. Your agents can now perform segmentation analysis on the fly to inform their next decision. Recording new actions is just as simple with `record_events`. Your agent logs these findings back to the dashboard, closing the loop on your data pipeline.

Setup guide

Set up Countly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Countly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Countly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Countly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Countly Agent",
            instructions="You have access to Countly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass the server URL to the `MCPServerStreamableHttp` constructor. Once you add it to your agent's list, the tools are discovered automatically. It's a standard setup for your Python workflow.

Yes, it uses the `update_user_details` tool. Your code sends the payload, and the agent updates the record in real-time. It keeps your analytics database accurate.

Your analytics data stays private. The server uses an endpoint token for all requests. No sensitive user IDs or behavioral logs are exposed to unauthorized processes during transport.

It does. You can use the `record_events` tool to push custom actions into your analytics stream. The agent handles the data formatting before sending it over.

The `read_drill` tool runs your query on the server side. You get a structured response that your agent can process or summarize. It keeps the heavy lifting off your local machine.

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