How to Use the Matomo MCP in AutoGen

Q: How do I configure the Matomo MCP server for AutoGen?

Install autogen-extmcp. Pass your Vinkius URL to StreamableHttpServerParams to generate the tools, then inject them into your AssistantAgent constructor.

Q: Can multiple AutoGen agents access Matomo tools simultaneously?

Yes. You can give getvisitssummary to one agent and getgoals to another. They will pull their respective data and debate the results in the shared chat.

Q: How does AutoGen handle Matomo API schemas?

The McpToolAdapter automatically translates the complex JSON outputs from tools like gettoppages into formats the agents can easily read and discuss.

Q: What happens to my Matomo user profiles in AutoGen?

Session data from getlivelastvisits remains strictly isolated. The Vinkius infrastructure runs the MCP connection in a secure V8 sandbox, meaning no personal identifiable information persists after the agent debate concludes.

Deploy AutoGen multi-agent teams to debate and analyze your Matomo web traffic.

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 AutoGen

Create your Vinkius account to connect Matomo to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Matomo MCP Server Analysis

The Matomo MCP Server equips your AutoGen agents to pull raw web metrics and debate their meaning. You assign `get_visits_summary` and `get_top_pages` to a data-gathering agent. This agent pulls the numbers and hands them over to a strategy agent that looks for drop-offs in the funnel. They don't just execute commands in a vacuum. A marketing agent might argue that a traffic spike is a success, while a conversion agent checks `get_goals` and points out that none of those new visitors actually bought anything. They negotiate until they reach a logical conclusion.

Audit Traffic Acquisition

Evaluating marketing spend requires looking at multiple referral sources simultaneously. Your agents use `get_top_referrers`, `get_top_websites`, and `get_top_socials` to build a complete map of inbound traffic. They compare these channels against historical baselines to spot anomalies. The system thrives on conflicting perspectives. One agent pushes to double down on a specific social network based on raw volume. Another agent reviews the bounce rates and argues for a different approach. You get a fully vetted recommendation.

Investigate Live User Sessions

Real-time debugging of site issues happens faster when agents collaborate. A monitoring agent constantly polls `get_live_last_visits` to watch for errors or sudden session terminations. When it spots a problem, it alerts a diagnostic agent. The diagnostic agent pulls the specific `get_visitor_profile` to trace exactly what the user clicked before leaving. It cross-references this with `get_site_details` to check for configuration issues. The agents work together to isolate the exact cause of the friction.

Setup guide

Set up Matomo MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Matomo tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Matomo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Matomo data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Matomo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Matomo data")
    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 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 AutoGen

Install `autogen-ext[mcp]`. Pass your Vinkius URL to `StreamableHttpServerParams` to generate the tools, then inject them into your `AssistantAgent` constructor.

Yes. You can give `get_visits_summary` to one agent and `get_goals` to another. They will pull their respective data and debate the results in the shared chat.

The `McpToolAdapter` automatically translates the complex JSON outputs from tools like `get_top_pages` into formats the agents can easily read and discuss.

Single agents often hallucinate insights from raw numbers. AutoGen forces multiple specialized agents to challenge each other's interpretations of your traffic data before presenting a final report.

Session data from `get_live_last_visits` remains strictly isolated. The Vinkius infrastructure runs the MCP connection in a secure V8 sandbox, meaning no personal identifiable information persists after the agent debate concludes.

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