How to Use the Matomo MCP in LlamaIndex

Q: How do I integrate the Matomo MCP server with LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it with McpToolSpec, convert it to an async tool list, and pass it to your FunctionAgent.

Q: Can LlamaIndex query Matomo visitor profiles for RAG?

It can. You pull session data using getvisitorprofile and index it. Your agent can then answer specific questions about user behavior based on that stored context.

Index your Matomo web analytics into LlamaIndex to build queryable, RAG-driven traffic reports.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Matomo MCP to LlamaIndex

Create your Vinkius account to connect Matomo to LlamaIndex 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 Matomo with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Traffic Patterns

The Matomo MCP Server allows your LlamaIndex setup to pull live web analytics and embed them into a searchable vector store. You run `get_visits_summary` and `get_top_pages`, and the system indexes these metrics alongside your internal documentation. Your RAG application now understands current site performance. This kills hallucinations. When you ask your agent why traffic dropped last week, it doesn't guess. It queries the index, retrieves the actual drop in numbers from the API, and gives you an answer grounded in hard data.

Build RAG with Matomo MCP Server

Connecting your analytics to a semantic search engine changes how you interact with traffic data. Your agent uses `get_top_referrers` and `get_top_socials` to build a localized knowledge base of your acquisition channels. You query your agent in plain English to find out which networks drive the most engagement. The agent cross-references this with historical data. If you ask about specific campaigns, it pulls the relevant documents and combines them with the live API output from `get_top_websites`. You get a complete picture of your marketing efforts.

Search Individual User Journeys

Detailed behavioral analysis requires granular data, which your agent grabs using `get_visitor_profile` and `get_live_last_visits`. LlamaIndex processes these specific session logs, making them available for complex semantic queries. You can ask your system to find users who exhibited specific navigation patterns. It links these journeys to broader site objectives. By indexing the output of `get_goals`, your application connects individual clicks to actual business outcomes. You build a knowledge base that explains exactly how users convert.

Setup guide

Set up Matomo MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Matomo MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Matomo tools.",
)
response = await agent.run("List recent Matomo data")

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 Matomo. 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 Matomo 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 Matomo MCP in LlamaIndex

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it with `McpToolSpec`, convert it to an async tool list, and pass it to your `FunctionAgent`.

It can. You pull session data using `get_visitor_profile` and index it. Your agent can then answer specific questions about user behavior based on that stored context.

Yes. You can restrict your agent to specific endpoints like `get_site_details` or `list_sites` using the allowed tools filter during setup.

You stop manually digging through analytics charts. LlamaIndex turns your raw traffic data from `get_top_pages` into a queryable knowledge base you can talk to.

The Vinkius zero-trust architecture ensures that raw metrics from `get_visits_summary` are handled ephemerally. The MCP connection authenticates via a single endpoint token, preventing unauthorized access to your core analytics database.

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