How to integrate Plausible Analytics MCP with Autogen

This guide walks you through connecting Plausible Analytics to AutoGen using the Composio tool router. By the end, you'll have a working Plausible Analytics agent that can summarize yesterday's traffic for your site, list top referrers from last week, compare pageviews across marketing campaigns through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Plausible Analytics account through Composio's Plausible Analytics MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Plausible Analytics logoPlausible Analytics
Api Key

Plausible Analytics is a privacy-focused web analytics platform for simple website stats. Use it to track traffic without cookies, clutter, or heavy scripts.

13 Tools

Introduction

This guide walks you through connecting Plausible Analytics to AutoGen using the Composio tool router. By the end, you'll have a working Plausible Analytics agent that can summarize yesterday's traffic for your site, list top referrers from last week, compare pageviews across marketing campaigns through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Plausible Analytics account through Composio's Plausible Analytics MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Plausible Analytics with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Plausible Analytics
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Plausible Analytics tools
  • Run a live chat loop where you ask the agent to perform Plausible Analytics operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Plausible Analytics MCP server, and what's possible with it?

The Plausible Analytics MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Plausible Analytics account. It provides structured and secure access to your website analytics, so your agent can monitor live visitors, analyze traffic trends, compare audience segments, review site settings, and record events on your behalf.

  • Live visitor monitoring: Have your agent check how many people visited your site during the last five minutes.
  • Traffic and trend analysis: Instruct your agent to query site statistics and retrieve visitor trends for a chosen time period.
  • Audience breakdowns: Let the agent break down your analytics by a selected dimension so you can compare traffic segments.
  • Site, goal, and access reviews: Direct your agent to list accessible sites, teams, goals, custom properties, and guests with dashboard access.
  • Pageview and custom event recording: Have your agent record pageviews or custom events in Plausible Analytics.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Plausible Analytics account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Plausible Analytics via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Plausible Analytics connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

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

load_dotenv()

async def main():
    # Initialize Composio and create a Plausible Analytics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["plausible_analytics"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Plausible Analytics tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Plausible Analytics assistant agent with MCP tools
    agent = AssistantAgent(
        name="plausible_analytics_assistant",
        description="An AI assistant that helps with Plausible Analytics operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Plausible Analytics tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Plausible Analytics related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Plausible Analytics tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Plausible Analytics and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

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

load_dotenv()

async def main():
    # Initialize Composio and create a Plausible Analytics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["plausible_analytics"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Plausible Analytics assistant agent with MCP tools
        agent = AssistantAgent(
            name="plausible_analytics_assistant",
            description="An AI assistant that helps with Plausible Analytics operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Plausible Analytics related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Plausible Analytics through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Plausible Analytics, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Plausible Analytics action and event your agent gets out of the box.

Check API Health

Tool to check the health status of the Plausible Analytics API.

Get Breakdown Stats

Tool to retrieve breakdown statistics for a specific property (dimension) from Plausible Analytics.

Get Plugin Capabilities

Tool to retrieve available capabilities for the Plausible Analytics Plugins API.

Get Realtime Visitors

Tool to retrieve the number of current visitors on your site in the last 5 minutes.

Get Site Details

Tool to retrieve details for a specific Plausible Analytics site.

Get Timeseries Stats

Tool to retrieve timeseries visitor data from Plausible Analytics over a specified time period.

List Custom Properties

Tool to list all custom properties configured for a site.

List Goals

Tool to list all goals configured for a site.

List Site Guests

Tool to list all guest users who have access to a site's dashboard in Plausible Analytics.

List Sites

Tool to list all sites the API key owner's Plausible account can access.

List Teams

Tool to list all teams available for the API key owner.

Query Analytics Stats

Tool to query analytics stats for a site using the Stats API v2.

Record Event

Tool to record a pageview or custom event via the Plausible Events API.

FRAMEWORKS

How to build Plausible Analytics MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Plausible Analytics MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Plausible Analytics MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Plausible Analytics MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Plausible Analytics MCP with Claude Cowork

Codex logo

Codex

Use Plausible Analytics MCP with Codex

OpenClaw logo

OpenClaw

Use Plausible Analytics MCP with OpenClaw

Hermes logo

Hermes

Use Plausible Analytics MCP with Hermes

CLI logo

CLI

Use Plausible Analytics MCP with CLI

Google ADK logo

Google ADK

Use Plausible Analytics MCP with Google ADK

LangChain logo

LangChain

Use Plausible Analytics MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Plausible Analytics MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Plausible Analytics MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Plausible Analytics MCP with LlamaIndex

CrewAI logo

CrewAI

Use Plausible Analytics MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Plausible Analytics MCP server, the agents and LLMs can only access a fixed set of Plausible Analytics tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Plausible Analytics and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Plausible Analytics tools.

Yes, absolutely. You can configure which Plausible Analytics scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Plausible Analytics data and credentials are handled as safely as possible.

Start with Plausible Analytics.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Plausible Analytics tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies