How to Use the Matomo Alternative MCP in LlamaIndex

Q: How do I get started with the Matomo Alternative and LlamaIndex?

First, pip install llama-index-tools-mcp. Then, create a BasicMCPClient with your server URL and pass it to McpToolSpec. The .totoollistasync() method gives you the tools for your agent.

Q: Can I limit which Matomo tools my LlamaIndex agent can use from this MCP server?

Yes. When you create the McpToolSpec, you can use the allowedtools filter to provide a specific list of tool names, like 'getvisitssummary', 'trackaction'. This is good for security and focus.

Q: Can I get visual charts from Matomo Alternative in my LlamaIndex app?

You can. The getimagegraph tool returns PNG data. Your LlamaIndex application can then save this data or display it, adding visual context to your analytics queries.

Index your live analytics data. Give your LlamaIndex RAG app a direct line to your Matomo reports and user tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Matomo Alternative MCP to LlamaIndex

Create your Vinkius account to connect Matomo Alternative 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 Alternative with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Reports into Knowledge

This isn't just about fetching data. With LlamaIndex, the output of `get_processed_report` becomes part of a searchable knowledge base. Your agent can pull a full analytics report and immediately index it into a vector store for later use. Now you can ask semantic questions about your analytics history. Instead of just pulling last week's report, you can ask "what were our top traffic sources during the summer sale?" and LlamaIndex will find the answer from the reports it has already indexed.

Real-Time Tracking for RAG

Your RAG application can now interact with the real world. Use the `track_action` tool to log an event in Matomo when a user interacts with your LlamaIndex-powered chatbot. This connects your agent's activity directly to your analytics. For higher volume, use `track_bulk` to batch events before sending. This is perfect for logging things like which documents were retrieved in a search session, giving you a rich dataset on how your RAG system is being used, all without overwhelming your analytics server.

Query Your MCP Server's Abilities

Your agent can query its own toolset. The `get_report_metadata` tool tells your LlamaIndex agent exactly what reports it can pull from the Matomo Alternative. This output can be indexed, making your agent self-aware of its analytics capabilities. This means you can build a query engine that first asks the MCP server what's possible, then executes the right reporting function. It's a way to build more robust agents that don't break when an underlying API changes.

Setup guide

Set up Matomo Alternative 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 Alternative 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 Alternative tools.",
)
response = await agent.run("List recent Matomo Alternative 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 Alternative 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 Alternative MCP in LlamaIndex

First, `pip install llama-index-tools-mcp`. Then, create a `BasicMCPClient` with your server URL and pass it to `McpToolSpec`. The `.to_tool_list_async()` method gives you the tools for your agent.

Yes. When you create the `McpToolSpec`, you can use the `allowed_tools` filter to provide a specific list of tool names, like `['get_visits_summary', 'track_action']`. This is good for security and focus.

It grounds your agent's knowledge in live data. You can index outputs from `get_processed_report` so when you ask about website performance, the answer comes from actual Matomo data, not just static documents.

You can. The `get_image_graph` tool returns PNG data. Your LlamaIndex application can then save this data or display it, adding visual context to your analytics queries.

Your data is only in transit. The MCP server runs in a zero-trust environment on Vinkius and is destroyed after each session. It never persists any of your analytics data, like `idsite` or user action details.

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