How to Use the Umami (Privacy Analytics) MCP in LangChain

Q: Can I monitor real-time activity using Umami (Privacy Analytics) and LangChain?

Absolutely. You can use the getrealtimestats tool to grab data from the last 30 minutes, letting your agent build immediate insights into current user behavior.

Q: How do I check who is on a team using Umami (Privacy Analytics) and LangChain?

You just call getteamusers. This tool returns the list of members, allowing your agent to verify access permissions or report membership data.

Q: Does Umami (Privacy Analytics) handle sensitive user identifiers in its data? (LangChain)

Yes. The server touches user IDs and session details. All data is handled within the secure, isolated MCP Server environment, giving you granular control over which information your agent processes.

Build complex analytics chains with Umami (Privacy Analytics) and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Umami (Privacy Analytics) MCP to LangChain

Create your Vinkius account to connect Umami (Privacy Analytics) 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 Umami (Privacy Analytics) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating multi-step reporting flows.

Need a full picture of performance? Your agent can build a chain that first checks the overall site health using `get_website_stats`. Next, it narrows the focus by calling `create_funnel_report` for conversion details. Finally, it stitches everything together into one actionable output via `create_attribution_report`.

Tracking user journeys from login to action.

You can model complex user paths in a single flow. Start by getting the session context with `get_session`, then follow up by checking activity using `get_session_activity`. This sequence allows your agent to see exactly how deep into the site the user went before sending an event via `send_event`.

Managing and provisioning entire team structures.

This MCP Server helps you govern the whole analytics ecosystem. Your chain can first list all teams using `list_teams`, then check if a user exists with `get_user`. If they don't, it runs `create_user` and finally assigns them to a group via `add_team_user`.

Setup guide

Set up Umami (Privacy Analytics) 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 Umami (Privacy Analytics) 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({
    "umami-privacy-analytics-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 Umami (Privacy Analytics) 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 Umami. 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 Umami (Privacy Analytics) 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 Umami (Privacy Analytics) MCP in LangChain

LangChain treats every tool call as a step in your reasoning chain. You can feed the output of `get_website_metrics` directly into an LLM prompt that decides which reporting function to run next.

Absolutely. You can use the `get_realtime_stats` tool to grab data from the last 30 minutes, letting your agent build immediate insights into current user behavior.

Your agent handles everything, including creating new teams (`create_team`) and managing website access. It also lets you delete entire sites using `delete_website`.

You just call `get_team_users`. This tool returns the list of members, allowing your agent to verify access permissions or report membership data.

Yes. The server touches `user IDs` and `session details`. All data is handled within the secure, isolated MCP Server environment, giving you granular control over which information your agent processes.

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