SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Keen io MCP with Pydantic AI

Connect Pydantic AI to Keen io MCP. List all event collections in your project, show unique user ids from purchases collection, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Keen io logoKeen io
Api Key

Keen io is an embedded analytics API for collecting, analyzing, and visualizing event data. It helps developers build powerful data-driven dashboards and insights into their apps.

6 Tools

Introduction

This guide walks you through connecting Keen io to Pydantic AI using the Composio tool router. By the end, you'll have a working Keen io agent that can inspect event collections and properties, select unique values, list cached datasets, and restore revoked access keys through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Keen io account through Composio's Keen io MCP server.

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

Also integrate Keen io with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Keen io
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Keen io workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Keen io MCP server, and what's possible with it?

The Keen io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Keen io account. It provides structured and secure access to your event data and analytics projects, so your agent can inspect event collections, analyze properties, fetch unique values, manage cached datasets, and even help with access key administration—all on your behalf.

  • Comprehensive event collection inspection: Let your agent list all event collections in your project and retrieve detailed schema information for each, so you always know what data is available.
  • Property analysis and schema insights: Have the agent dive into specific properties within a collection to reveal inferred types and resource URLs for precise data understanding.
  • Unique value extraction: Direct your agent to fetch all unique values for any property across your events, making it easy to spot trends, segments, or outliers in your analytics.
  • Cached dataset management: Ask your agent to list and page through all cached dataset definitions in your Keen io project for streamlined reporting and analysis workflows.
  • Access key administration: Instruct your agent to unrevoke previously revoked API keys, helping you quickly restore secure access when needed.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Keen io
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Keen io
  • MCPServerStreamableHTTP connects to the Keen io MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Keen io
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["keen_io"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Keen io tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
keen_io_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[keen_io_mcp],
    instructions=(
        "You are a Keen io assistant. Use Keen io tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Keen io endpoint
  • The agent uses GPT-5 to interpret user commands and perform Keen io operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Keen io.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Keen io API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Keen io and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Keen io
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["keen_io"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    keen_io_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[keen_io_mcp],
        instructions=(
            "You are a Keen io assistant. Use Keen io tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Keen io.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Keen io through Composio's Tool Router. With this setup, your agent can perform real Keen io actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Keen io for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Keen io action and event your agent gets out of the box.

Inspect All Event Collections

Retrieve schema information for all event collections in a Keen.

Inspect Collection Property

Tool to return details for a specific property in an event collection.

Inspect Single Event Collection

Retrieve schema information for a single Keen.

List Cached Dataset Definitions

List all cached dataset definitions for a Keen.

Select Unique

Return unique values for a target property among events in a collection over a required timeframe, with optional filters.

Unrevoke Access Key

Reactivate a previously revoked Keen.

FRAMEWORKS

How to build Keen io MCP Agent with another framework

Claude Code logo

Claude Code

Use Keen io MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Keen io MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Keen io MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Keen io MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Keen io MCP with Grok Bot

Codex logo

Codex

Use Keen io MCP with Codex

OpenClaw logo

OpenClaw

Use Keen io MCP with OpenClaw

Hermes logo

Hermes

Use Keen io MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Keen io MCP with Atomic Agent

Google ADK logo

Google ADK

Use Keen io MCP with Google ADK

LangChain logo

LangChain

Use Keen io MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Keen io MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Keen io MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Keen io MCP with LlamaIndex

CrewAI logo

CrewAI

Use Keen io MCP with CrewAI

AutoGen logo

AutoGen

Use Keen io MCP with AutoGen

FAQ

Frequently asked questions

Start with Keen io.It takes 30 seconds.

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

Start building