How to Use the Piwik PRO MCP in LangChain

Q: How do I use LangChain to run a custom Piwik PRO analytics query?

Get the tools from the MCP client and pass them to a createagent function. The agent will then have access to querypiwikanalytics and can decide when to use it based on your prompt.

Q: Can my LangChain agent list all available dashboards in Piwik PRO?

Yes, the agent can call listpiwikdashboards to get a list of all available dashboards. This is just another tool call within your MCP integration.

Q: What's the best way to chain Piwik PRO tool calls in LangChain?

Start by having the agent call listpiwikapps or listpiwiksites. Then, feed the id from the output into the idSite parameter for listpiwikgoals or querypiwikanalytics.

Q: Is it possible to track conversion goals from Piwik PRO with a LangChain agent?

Definitely. The agent uses listpiwikgoals to understand the goal definitions. It then calls querypiwikanalytics to fetch the actual performance data for those goals.

Build analytics chains for Piwik PRO with LangChain. Turn raw data into answers, one step at a time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Piwik PRO MCP to LangChain

Create your Vinkius account to connect Piwik PRO to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Piwik PRO with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Query Piwik PRO in a Chain

Your agent can now run a sequence of analytics operations. First, it calls `list_piwik_sites` to find the correct site ID. Then it uses that ID to call `list_piwik_goals` and identify the specific conversion you're tracking. With that context, it constructs a precise request to `query_piwik_analytics`. The output isn't just a number; it's the result of a multi-step reasoning process that you can trace from start to finish.

Trace Every Analytics Call

Stop guessing why a query failed. LangChain's observability lets you see the exact JSON payload your agent sent to `query_piwik_analytics`. You can debug complex filters and dimensions right in your trace. This makes fixing broken analytics logic simple. You see the input, the tool call, and the raw output from the Piwik PRO API. No more black boxes.

Your Piwik PRO MCP Server

Piwik PRO data is more useful when it's connected to other tools. Your LangChain agent can pull metrics with `query_piwik_analytics`, grab related customer data from a SQL database, and then post a summary to your team's messaging app. This isn't just about reading data. It's about building automated workflows that react to your analytics in real time.

Setup guide

Set up Piwik PRO 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 Piwik PRO 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({
    "piwik-pro-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 Piwik PRO 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 Piwik PRO. 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 Piwik PRO 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 Piwik PRO MCP in LangChain

Get the tools from the MCP client and pass them to a `create_agent` function. The agent will then have access to `query_piwik_analytics` and can decide when to use it based on your prompt.

Yes, the agent can call `list_piwik_dashboards` to get a list of all available dashboards. This is just another tool call within your MCP integration.

Start by having the agent call `list_piwik_apps` or `list_piwik_sites`. Then, feed the `id` from the output into the `idSite` parameter for `list_piwik_goals` or `query_piwik_analytics`.

Definitely. The agent uses `list_piwik_goals` to understand the goal definitions. It then calls `query_piwik_analytics` to fetch the actual performance data for those goals.

Your connection is secured through the Vinkius endpoint. Access to user PII via `list_piwik_users` is controlled by the API key permissions you configure in Piwik PRO. LangChain simply executes the tool call; it doesn't store user data by default.

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