How to integrate Mixpanel MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Mixpanel logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Mixpanel to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Mixpanel agent that can show daily active users for last month, list top events by user engagement, analyze conversion funnel for signup flow through natural language commands.

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

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

Also integrate Mixpanel with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Mixpanel integration
  • Using Composio's Tool Router to dynamically load and access Mixpanel tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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

The Mixpanel MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mixpanel account. It provides structured and secure access to your product analytics data, so your agent can perform actions like retrieving event metrics, analyzing cohorts, exploring funnels, and running custom queries on your behalf.

  • Event property and trend analysis: Ask your agent to fetch unique, total, or average values for specific events and properties over time to spot trends and measure engagement.
  • Cohort and funnel exploration: Have your agent pull lists of saved cohorts or funnels, or retrieve detailed funnel performance data to understand user journeys.
  • User activity and frequency reporting: Direct your agent to analyze how frequently users perform key events or to get event activity feeds for individual profiles.
  • Custom JQL query execution: Run advanced, custom JavaScript queries through your agent for deep, flexible analytics tailored to your business questions.
  • Project and configuration management: Let your agent list all Mixpanel projects under your account, giving you quick access to metadata and configuration details.

Supported Tools & Triggers

Tools
Add Unique Values to Profile List PropertyTool to add unique values to list properties on user profiles in Mixpanel using the $union operation.
Get Aggregated Event Property ValuesGet unique, total, or average data for a single event and property over days, weeks, or months.
Get Aggregate EventsGet aggregate event counts over time.
List Saved CohortsTool to list all saved cohorts in a Mixpanel project.
Create Annotation TagTool to create a new annotation tag in Mixpanel using the provided name.
Create IdentityTool to create an identity mapping in Mixpanel by linking an anonymous ID with an identified user ID.
Create Service AccountTool to create a new service account for your organization and optionally add it to projects.
Delete GroupTool to permanently delete a group profile from Mixpanel Group Analytics.
Delete ProfileTool to permanently delete a user profile from Mixpanel, along with all of its properties.
Delete Multiple Profiles (Batch)Tool to permanently delete multiple user profiles from Mixpanel in a single batch request.
Delete Profile PropertyTool to permanently delete properties from a Mixpanel user profile using the $unset operation.
Get All ProjectsGet all projects associated with the authenticated Mixpanel account.
Get Annotation TagsTool to get all annotation tags from a Mixpanel project.
Batch Update Group ProfilesTool to send a batch of group profile updates to Mixpanel.
Delete Group PropertiesTool to delete specific properties from a Mixpanel group profile.
Create Identity AliasTool to create an alias mapping between two distinct IDs in Mixpanel.
Execute JQL QueryExecute a custom JQL (JavaScript Query Language) query against Mixpanel's Query API.
List Saved FunnelsGet the names and funnel_ids of your funnels.
List Service AccountsTool to list all service accounts for an organization.
Append to Profile List PropertyTool to append values to list properties on user profiles in Mixpanel.
Update Multiple Profiles (Batch)Tool to update multiple user profiles in Mixpanel in a single batch request.
Get Profile Event ActivityGet event activity feed for specified users from Mixpanel Query API.
Increment Profile Numerical PropertyTool to increment or decrement numerical properties on user profiles in Mixpanel.
Remove from Profile List PropertyTool to remove values from list properties on user profiles in Mixpanel.
Set Profile PropertiesTool to set user profile properties in Mixpanel using the $set operation.
Query Frequency ReportGet data about how frequently users are performing events.
Query Saved FunnelGet data for a funnel.
Query Saved InsightGet data from your Insights reports.
Query Numeric Average ReportAverages an expression for events per unit time.
Query Numeric Sum ReportSums an expression for events per unit time.
Query ProfilesQuery user or group profile data from Mixpanel.
Query Retention ReportQuery cohort analysis showing user retention patterns over time.
Query Segmentation ReportGet data for an event, segmented and filtered by properties with daily/time-series breakdown.
Query Top EventsGet the top events for today, with their counts and the normalized percent change from yesterday.
Remove from Group List PropertyTool to remove values from list properties on group profiles in Mixpanel.
Remove from Profile List PropertyTool to remove values from list properties on user profiles in Mixpanel using the $remove operation.
Numeric Bucket Segmentation QueryTool to get event data numerically bucketed by property values.
Set Group Property OnceTool to set properties on a Mixpanel group profile only if they don't already exist.
Set Profile Property OnceTool to set user profile properties in Mixpanel using the $set_once operation.
Get Top Event PropertiesGet the top property names for an event.
Get Top Event Property ValuesTool to get the top values for a property ordered by frequency.
Get Top EventsGet a list of the most common events over the last 31 days.
Union to Group List PropertyTool to add unique values to list properties on group profiles in Mixpanel.

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

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["mixpanel"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Mixpanel tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Mixpanel-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Mixpanel tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to mixpanel, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Mixpanel tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Mixpanel and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["mixpanel"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to mixpanel, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Mixpanel agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Mixpanel MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Mixpanel MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Mixpanel MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Mixpanel MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Mixpanel MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Mixpanel MCP with Claude Cowork

Codex logo

Codex

Use Mixpanel MCP with Codex

Cursor logo

Cursor

Use Mixpanel MCP with Cursor

OpenClaw logo

OpenClaw

Use Mixpanel MCP with OpenClaw

Hermes logo

Hermes

Use Mixpanel MCP with Hermes

CLI logo

CLI

Use Mixpanel MCP with CLI

Google ADK logo

Google ADK

Use Mixpanel MCP with Google ADK

LangChain logo

LangChain

Use Mixpanel MCP with LangChain

Mastra AI logo

Mastra AI

Use Mixpanel MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Mixpanel MCP with LlamaIndex

CrewAI logo

CrewAI

Use Mixpanel MCP with CrewAI

OpenCode logo

OpenCode

Use Mixpanel MCP with OpenCode

VS Code logo

VS Code

Use Mixpanel MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Mixpanel MCP?

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

Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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 Mixpanel tools.

Can I manage the permissions and scopes for Mixpanel while using Tool Router?

Yes, absolutely. You can configure which Mixpanel 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.

How safe is my data with Composio Tool Router?

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 Mixpanel data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗