How to Use the Piwik PRO MCP in AutoGen

Q: How do I give different AutoGen agents access to different Piwik PRO tools?

When you create each AssistantAgent, pass it a specific list of tools from the mcpservertools function. This lets you restrict which agent can call sensitive functions like listpiwikusers.

Q: How does this Piwik PRO MCP server work with AutoGen's model?

The tools, like listpiwikdashboards, are exposed as functions the agents can execute. An agent calls a tool, and the output is posted back into the group chat as a message for all agents to see and react to.

Let your AI agents debate Piwik PRO analytics. Get to the right decision with AutoGen's conversational MCP framework.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate Analytics Strategy

Don't just get a number; get a consensus. You can create an "Analyst" agent that uses `query_piwik_analytics` to pull metrics. At the same time, a "Strategist" agent can call `list_piwik_goals` to review your objectives. These two agents then discuss the findings in a group chat. They can challenge each other's interpretations and work together to propose a course of action, like updating a goal or launching a new test.

Assign Roles for Safer Queries

Build checks and balances directly into your agent workflow. For instance, create a "Compliance" agent that must approve any call to the `list_piwik_users` tool. It's the only agent with access to that function. Meanwhile, a "Data" agent can freely run `query_piwik_analytics` but is blocked from seeing user lists. AutoGen's multi-agent conversations let you enforce separation of duties automatically.

Your Piwik PRO MCP Server

Assemble a specialized reporting team made of AI agents. One agent's only job is to run a daily `query_piwik_analytics` for your main KPIs. A second agent takes that data, compares it to the targets defined in `list_piwik_goals`, and writes a plain-English summary. A third "Manager" agent reviews the summary and decides if a human needs to be alerted. This MCP Server gives your agent team the specific tools they need to collaborate effectively.

Setup guide

Set up Piwik PRO 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 Piwik PRO 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="Piwik PRO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Piwik PRO 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="Piwik PRO_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Piwik PRO 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 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 AutoGen

When you create each `AssistantAgent`, pass it a specific list of tools from the `mcp_server_tools` function. This lets you restrict which agent can call sensitive functions like `list_piwik_users`.

Yes, that's a core AutoGen pattern. You can have one agent call `query_piwik_analytics` and then require a second 'Auditor' agent to confirm the query parameters or results before the conversation continues.

Definitely. You can set up a recurring conversation where an agent calls `query_piwik_analytics` for goal data, and then reports to a 'Manager' agent if performance drops below a set threshold.

The tools, like `list_piwik_dashboards`, are exposed as functions the agents can execute. An agent calls a tool, and the output is posted back into the group chat as a message for all agents to see and react to.

Safety depends on your design. The best practice is to create one specialized agent that is the only one with permission to call `list_piwik_users`. While Vinkius encrypts the transport, managing the data flow between your agents is critical for privacy.

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