How to Use the Countly MCP in LangChain

Build chains that track product behavior by feeding Countly data directly into your LangChain 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 LangChain

Create your Vinkius account to connect Countly to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain analytics into your LangChain logic

Trigger `read_metrics` or `read_drill` to pull raw numbers into your chain. The agent processes these results as input for the next step, letting you build automated reports without manual intervention. Connect the `record_events` tool to log chain actions back into your dashboard. You get a live feedback loop where your pipeline observes its own performance.

Manage user sessions from your LangChain flow

Use `begin_session` and `update_session` to track state during complex multi-step tasks. Your agent maintains context of the user interaction throughout the entire execution chain. Close out tasks cleanly with `end_session` once the logic completes. This ensures your analytics accurately reflect the lifecycle of the agent's work.

Update user profiles via LangChain

Push data changes to your backend using `update_user_details`. Your agent reads information from external sources and syncs it with your analytics platform immediately. Verify these updates by calling `read_events` to confirm the change was logged. It keeps your data consistent without any manual data entry.

Setup guide

Set up Countly MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Countly tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "countly-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Countly transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapters and initialize the server via the MultiServerMCPClient. You then pass the tool list directly into your agent constructor to start making calls.

Yes, you can bind the record tools to your agent's output. Every time the agent finishes a step, it logs an event to your dashboard.

Data privacy is handled at the transport layer. The MCP server only exposes the functions you permit, and all traffic remains within your controlled environment.

It does. You can trigger custom events using the provided tools whenever your pipeline hits a specific milestone.

This server accesses user identification strings and interaction timestamps. All data is scoped to the specific sessions your agent initiates.

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