How to Use the Piwik PRO MCP in LlamaIndex

Q: How can I build a RAG pipeline with LlamaIndex and Piwik PRO data?

Use the McpToolSpec to load the tools into a FunctionAgent. The agent can then call querypiwikanalytics and you can configure a pipeline to automatically index the results into your vector store.

Q: What tools are available for inspecting my Piwik PRO account with LlamaIndex?

This MCP server provides tools to listpiwiksites, listpiwikapps, listpiwikdashboards, and listpiwikgoals. You can use them to build a complete, queryable picture of your analytics setup.

Turn your Piwik PRO data into a queryable knowledge base with LlamaIndex. Ask questions, get answers from your own analytics.

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 LlamaIndex

Create your Vinkius account to connect Piwik PRO to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Your Analytics

Don't just run a query once. With LlamaIndex, the output of every call to `query_piwik_analytics` can be ingested and indexed into a vector store. This builds a memory of your historical performance data. Your agent can then answer questions about trends over time without repeatedly hitting the Piwik PRO API. It's querying a local, structured knowledge base built from your own metrics.

Ground Answers in Real Data

Agent hallucinations about metrics are a real problem. LlamaIndex solves this by grounding its responses in retrieved data. When you ask about last month's conversion rate, the agent pulls the answer from its indexed `query_piwik_analytics` results. This Retrieval-Augmented Generation (RAG) approach means you get answers based on facts, not fiction. The agent combines live API calls with its knowledge base for verifiable accuracy.

Query Your Piwik PRO MCP Server

Your Piwik PRO configuration is now a searchable resource. Run `list_piwik_goals` and `list_piwik_dashboards` once, and let LlamaIndex index the output. Your setup becomes self-documenting. Later, anyone can ask the agent, "What goals are we tracking for the iOS app?" and get an immediate, accurate answer. This MCP Server makes your configuration transparent and easy to inspect.

Setup guide

Set up Piwik PRO 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 Piwik PRO 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 Piwik PRO tools.",
)
response = await agent.run("List recent Piwik PRO 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 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 LlamaIndex

Use the `McpToolSpec` to load the tools into a `FunctionAgent`. The agent can then call `query_piwik_analytics` and you can configure a pipeline to automatically index the results into your vector store.

Yes, that's what it's built for. This MCP server lets LlamaIndex do what it does best: index tool outputs to create a long-term memory of your analytics data that the agent can search.

It uses a RAG pipeline. The agent first searches its indexed knowledge base—built from real `query_piwik_analytics` outputs—and uses that data to construct its answer.

This MCP server provides tools to `list_piwik_sites`, `list_piwik_apps`, `list_piwik_dashboards`, and `list_piwik_goals`. You can use them to build a complete, queryable picture of your analytics setup.

LlamaIndex processes the data your agent retrieves. When you call `list_piwik_users`, it's your decision whether to index that user information. Your Vinkius endpoint secures the transport, but data residency and privacy depend on your vector database's configuration.

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