# How to integrate Mixpanel MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Mixpanel MCP with Vercel AI SDK v6", "toolkit": "Mixpanel", "toolkit_slug": "mixpanel", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/mixpanel/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/mixpanel/framework/ai-sdk.md", "updated_at": "2026-05-12T10:19:12.314Z" } ``` ## 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 - [ChatGPT](https://composio.dev/toolkits/mixpanel/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/mixpanel/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/mixpanel/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/mixpanel/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/mixpanel/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/mixpanel/framework/codex) - [Cursor](https://composio.dev/toolkits/mixpanel/framework/cursor) - [VS Code](https://composio.dev/toolkits/mixpanel/framework/vscode) - [OpenCode](https://composio.dev/toolkits/mixpanel/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/mixpanel/framework/openclaw) - [Hermes](https://composio.dev/toolkits/mixpanel/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/mixpanel/framework/cli) - [Google ADK](https://composio.dev/toolkits/mixpanel/framework/google-adk) - [LangChain](https://composio.dev/toolkits/mixpanel/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/mixpanel/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/mixpanel/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/mixpanel/framework/crew-ai) ## 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 | Tool slug | Name | Description | |---|---|---| | `MIXPANEL_ADD_UNIQUE_TO_PROFILE_LIST_PROPERTY` | Add Unique Values to Profile List Property | Tool to add unique values to list properties on user profiles in Mixpanel using the $union operation. Use when you need to add items to list-type properties without creating duplicates. Unlike $append, $union ensures values are unique in the list. If the property doesn't exist, it creates a new list with the provided values. | | `MIXPANEL_AGGREGATED_EVENT_PROPERTY_VALUES` | Get Aggregated Event Property Values | Get unique, total, or average data for a single event and property over days, weeks, or months. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_AGGREGATE_EVENTS` | Get Aggregate Events | Get aggregate event counts over time. Supports different types of aggregation: general, unique, average, sum. | | `MIXPANEL_COHORTS_LIST` | List Saved Cohorts | Tool to list all saved cohorts in a Mixpanel project. Use when you need to retrieve cohort metadata including name, id, count, description, creation date, and visibility. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_CREATE_ANNOTATION_TAG` | Create Annotation Tag | Tool to create a new annotation tag in Mixpanel using the provided name. Use when you need to create tags for organizing and categorizing annotations. Requires a role of at least Analyst. | | `MIXPANEL_CREATE_IDENTITY` | Create Identity | Tool to create an identity mapping in Mixpanel by linking an anonymous ID with an identified user ID. Use when you need to connect pre-login anonymous activity with post-login identified user activity. This operation is typically performed after user authentication to associate all previous anonymous events with the user's identified profile. | | `MIXPANEL_CREATE_SERVICE_ACCOUNT` | Create Service Account | Tool to create a new service account for your organization and optionally add it to projects. Use when you need to generate API credentials for programmatic access. The response includes a token (secret) that cannot be recovered after creation. Requires service account with admin or owner role. | | `MIXPANEL_DELETE_GROUP` | Delete Group | Tool to permanently delete a group profile from Mixpanel Group Analytics. Use when you need to completely remove a group profile and all of its properties. The deletion is permanent and cannot be undone. Note that group properties on historical events remain intact even after group deletion. | | `MIXPANEL_DELETE_PROFILE` | Delete Profile | Tool to permanently delete a user profile from Mixpanel, along with all of its properties. Use when you need to completely remove a profile. The deletion is permanent and cannot be undone. Note that this only deletes the profile, not the associated events. For duplicate profiles, use $ignore_alias: true to avoid deleting the original profile. | | `MIXPANEL_DELETE_PROFILE_BATCH` | Delete Multiple Profiles (Batch) | Tool to permanently delete multiple user profiles from Mixpanel in a single batch request. Use when you need to delete multiple profiles efficiently. The deletion is permanent and cannot be undone. This only deletes the profiles, not the associated events. For duplicate profiles, use $ignore_alias: true to avoid deleting the original profile. | | `MIXPANEL_DELETE_PROFILE_PROPERTY` | Delete Profile Property | Tool to permanently delete properties from a Mixpanel user profile using the $unset operation. Use when you need to remove specific properties and their values from a profile. Properties are permanently removed and cannot be recovered. Useful when cleaning up properties or approaching Mixpanel's limit of 2000 properties per profile. | | `MIXPANEL_GET_ALL_PROJECTS` | Get All Projects | Get all projects associated with the authenticated Mixpanel account. Returns project details including name, permissions, role, domain, and other configuration details. If a project appears inaccessible, verify the connection region matches the project's cluster before assuming a permissions issue. | | `MIXPANEL_GET_ANNOTATION_TAGS_ALT1` | Get Annotation Tags | Tool to get all annotation tags from a Mixpanel project. Use when you need to retrieve tags that have been added to annotations. Requires a role of at least Analyst. | | `MIXPANEL_GROUP_BATCH_UPDATE` | Batch Update Group Profiles | Tool to send a batch of group profile updates to Mixpanel. Use when you need to update multiple group profiles in a single request. Supports operations like $set, $set_once, $union, $remove, $unset, and $delete. Note: $add is NOT supported for group profiles. | | `MIXPANEL_GROUP_DELETE_PROPERTY` | Delete Group Properties | Tool to delete specific properties from a Mixpanel group profile. Use when you need to permanently remove unwanted properties from a group (company, organization, team, etc.). The operation uses the $unset operation to permanently remove the specified properties. | | `MIXPANEL_IDENTITY_CREATE_ALIAS` | Create Identity Alias | Tool to create an alias mapping between two distinct IDs in Mixpanel. Use when you need to link a new identifier with an existing one. This is only available for projects using the Original ID Merge system and Legacy ID Management System; it has no effect in the Simplified ID Merge system. Typically called once during user signup to connect anonymous pre-signup events with post-signup activity. Each alias can only map to one distinct_id. | | `MIXPANEL_JQL_QUERY` | Execute JQL Query | Execute a custom JQL (JavaScript Query Language) query against Mixpanel's Query API. Key Constraints: - 60 queries/hour, max 5 concurrent queries. - 2-minute execution timeout. - 5 GB data processing limit, 2 GB output limit. - No remote network requests (XMLHttpRequest) are allowed inside the JQL script. | | `MIXPANEL_LIST_FUNNELS` | List Saved Funnels | Get the names and funnel_ids of your funnels. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_LIST_SERVICE_ACCOUNTS` | List Service Accounts | Tool to list all service accounts for an organization. Use when you need to retrieve service accounts, check when they were last used, or see when they expire. Requires service account with admin or owner role. | | `MIXPANEL_PROFILE_APPEND_TO_LIST_PROPERTY` | Append to Profile List Property | Tool to append values to list properties on user profiles in Mixpanel. Use when you need to add items to list-type properties. Unlike $union, $append allows duplicate values. If the property doesn't exist, it creates a new list with the value as the first element. | | `MIXPANEL_PROFILE_BATCH_UPDATE` | Update Multiple Profiles (Batch) | Tool to update multiple user profiles in Mixpanel in a single batch request. Use when you need to update properties for multiple users efficiently. Supports operations: $set (update/add), $set_once (set if not exists), $add (increment), $union (add to list uniquely), $append (append to list), $remove (remove from list), $unset (delete property), $delete (delete profile). Maximum 50 updates per request. Always check the response status and failed_records for individual update failures. | | `MIXPANEL_PROFILE_EVENT_ACTIVITY` | Get Profile Event Activity | Get event activity feed for specified users from Mixpanel Query API. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_PROFILE_NUMERICAL_ADD` | Increment Profile Numerical Property | Tool to increment or decrement numerical properties on user profiles in Mixpanel. Use when you need to add values to existing numerical properties (e.g., login counts, points, credits). Properties are incremented by the specified amount. If a property doesn't exist, the value is added to zero. Use negative values to decrement properties. | | `MIXPANEL_PROFILE_REMOVE_FROM_LIST_PROPERTY` | Remove from Profile List Property | Tool to remove values from list properties on user profiles in Mixpanel. Use when you need to remove specific items from list-type properties. If the value doesn't exist in the list, no updates are made. If the property doesn't exist or is not list-valued, the operation is ignored. | | `MIXPANEL_PROFILE_SET` | Set Profile Properties | Tool to set user profile properties in Mixpanel using the $set operation. Use when you need to create or update properties on a user profile. Properties specified will be created if they don't exist, or overwritten if they do. If the profile doesn't exist, it will be created with these properties. | | `MIXPANEL_QUERY_FREQUENCY_REPORT` | Query Frequency Report | Get data about how frequently users are performing events. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. Example response with unit="day" and addiction_unit="hour": { "2012-01-01": [305, 107, 60, 41, ...], # Users who did event in 1+ hours, 2+ hours, etc. "2012-01-02": [495, 204, 117, 77, ...], "2012-01-03": [671, 324, 176, 122, ...] } | | `MIXPANEL_QUERY_FUNNEL` | Query Saved Funnel | Get data for a funnel. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_QUERY_INSIGHT` | Query Saved Insight | Get data from your Insights reports. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_QUERY_NUMERIC_AVERAGE` | Query Numeric Average Report | Averages an expression for events per unit time. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. Example response: { "status": "ok", "results": { "2024-01-01": 25.5, "2024-01-02": 32.75, "2024-01-03": 28.25 } } | | `MIXPANEL_QUERY_NUMERIC_SUM` | Query Numeric Sum Report | Sums an expression for events per unit time. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. Example response: { "status": "ok", "computed_at": "2024-01-20T12:00:00", "results": { "2024-01-01": 150.5, "2024-01-02": 245.75, "2024-01-03": 198.25 } } | | `MIXPANEL_QUERY_PROFILES` | Query Profiles | Query user or group profile data from Mixpanel. Returns list of profiles that match specified parameters. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_QUERY_RETENTION_REPORT` | Query Retention Report | Query cohort analysis showing user retention patterns over time. Tracks how users who performed an initial event (born_event) subsequently perform a target event (event). Use the 'unit' parameter to control cohort interval granularity ('day', 'week', 'month'); defaults to 'day'. | | `MIXPANEL_QUERY_SEGMENTATION` | Query Segmentation Report | Get data for an event, segmented and filtered by properties with daily/time-series breakdown. Use the 'unit' parameter to control time bucketing ('minute', 'hour', 'day', 'month'). The Query API has a rate limit of 60 queries per hour and 5 concurrent queries, shared across related tools (e.g., MIXPANEL_JQL_QUERY, MIXPANEL_TOP_EVENT_PROPERTY_VALUES); bursts of concurrent calls return 429. | | `MIXPANEL_QUERY_TOP_EVENTS` | Query Top Events | Get the top events for today, with their counts and the normalized percent change from yesterday. Use when you need to analyze today's event performance compared to yesterday. | | `MIXPANEL_REMOVE_FROM_GROUP_LIST_PROPERTY` | Remove from Group List Property | Tool to remove values from list properties on group profiles in Mixpanel. Use when you need to remove specific items from list-type properties on groups (companies, organizations, etc.). If the value doesn't exist in the list, no updates are made. If the property doesn't exist or is not list-valued, the operation is ignored. | | `MIXPANEL_REMOVE_FROM_LIST_PROPERTY` | Remove from Profile List Property | Tool to remove values from list properties on user profiles in Mixpanel using the $remove operation. Use when you need to remove specific items from list-type properties. If the value doesn't exist in the list, no action is taken. The profile will be created if it doesn't exist. | | `MIXPANEL_SEGMENTATION_NUMERIC_QUERY` | Numeric Bucket Segmentation Query | Tool to get event data numerically bucketed by property values. Use when you need to analyze distributions of numeric properties like revenue, session duration, or counts with automatic bucketing. | | `MIXPANEL_SET_GROUP_PROPERTY_ONCE` | Set Group Property Once | Tool to set properties on a Mixpanel group profile only if they don't already exist. Use when you need to set initial properties for a group without overwriting existing values. Ideal for setting default values or tracking when a group was first created. Properties that already exist will not be modified. | | `MIXPANEL_SET_PROFILE_PROPERTY_ONCE` | Set Profile Property Once | Tool to set user profile properties in Mixpanel using the $set_once operation. Use when you need to set properties that should only be recorded on their initial value. Properties specified will be created only if they don't already exist on the profile. If a property already has a value, it will not be overwritten. Ideal for tracking first-time values like signup source, initial referrer, or first login date. | | `MIXPANEL_TOP_EVENT_PROPERTIES` | Get Top Event Properties | Get the top property names for an event. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_TOP_EVENT_PROPERTY_VALUES` | Get Top Event Property Values | Tool to get the top values for a property ordered by frequency. Use when you need to understand the most common values for a specific property on an event. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. This limit is shared across all Query API tools (e.g., MIXPANEL_QUERY_SEGMENTATION); on a 429 response, apply exponential backoff. | | `MIXPANEL_TOP_EVENTS` | Get Top Events | Get a list of the most common events over the last 31 days. The Query API has a rate limit of 60 queries per hour and a maximum of 5 concurrent queries. | | `MIXPANEL_UPDATE_GROUP_LIST_PROPERTY` | Union to Group List Property | Tool to add unique values to list properties on group profiles in Mixpanel. Use when you need to add items to list-type group properties without creating duplicates. The $union operation ensures that values are only added if they don't already exist in the list. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Mixpanel MCP server is an implementation of the Model Context Protocol that connects your AI agent to Mixpanel. It provides structured and secure access so your agent can perform Mixpanel operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before you begin, make sure you have: - Node.js and npm installed - A Composio account with API key - An OpenAI API key ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install required dependencies 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 ```bash npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv ``` ### 3. Set up environment variables 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 ```bash OPENAI_API_KEY=your_openai_api_key_here COMPOSIO_API_KEY=your_composio_api_key_here COMPOSIO_USER_ID=your_user_id_here ``` ### 4. Import required modules and validate environment 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 ```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, }); ``` ### 5. Create Tool Router session and initialize MCP client 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 ```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; ``` ### 6. Connect to MCP server and retrieve 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 ```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(); ``` ### 7. Initialize conversation and CLI interface 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 ```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(); ``` ### 8. Handle user input and stream responses with real-time tool feedback 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 ```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); }); ``` ## Complete Code ```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](https://composio.dev/toolkits/mixpanel/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/mixpanel/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/mixpanel/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/mixpanel/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/mixpanel/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/mixpanel/framework/codex) - [Cursor](https://composio.dev/toolkits/mixpanel/framework/cursor) - [VS Code](https://composio.dev/toolkits/mixpanel/framework/vscode) - [OpenCode](https://composio.dev/toolkits/mixpanel/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/mixpanel/framework/openclaw) - [Hermes](https://composio.dev/toolkits/mixpanel/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/mixpanel/framework/cli) - [Google ADK](https://composio.dev/toolkits/mixpanel/framework/google-adk) - [LangChain](https://composio.dev/toolkits/mixpanel/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/mixpanel/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/mixpanel/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/mixpanel/framework/crew-ai) ## Related Toolkits - [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources. - [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research. - [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows. - [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research. - [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data. - [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds. - [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights. - [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly. - [Bright Data MCP](https://composio.dev/toolkits/brightdata_mcp) - Bright Data MCP is an AI-powered web scraping and data collection platform. Instantly access public web data in real time with advanced scraping tools. - [Browseai](https://composio.dev/toolkits/browseai) - Browseai is a web automation and data extraction platform that turns any website into an API. It's perfect for monitoring websites and retrieving structured data without manual scraping. - [ClickHouse](https://composio.dev/toolkits/clickhouse) - ClickHouse is an open-source, column-oriented database for real-time analytics and big data processing using SQL. Its lightning-fast query performance makes it ideal for handling large datasets and delivering instant insights. - [Coinmarketcal](https://composio.dev/toolkits/coinmarketcal) - CoinMarketCal is a community-powered crypto calendar for upcoming events, announcements, and releases. It helps traders track market-moving developments and stay ahead in the crypto space. - [Control d](https://composio.dev/toolkits/control_d) - Control d is a customizable DNS filtering and traffic redirection platform. It helps you manage internet access, enforce policies, and monitor usage across devices and networks. - [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights. - [Databricks](https://composio.dev/toolkits/databricks) - Databricks is a unified analytics platform for big data and AI on the lakehouse architecture. It empowers data teams to collaborate, analyze, and build scalable solutions efficiently. - [Datagma](https://composio.dev/toolkits/datagma) - Datagma delivers data intelligence and analytics for business growth and market discovery. Get actionable market insights and track competitors to inform your strategy. - [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment. - [Dovetail](https://composio.dev/toolkits/dovetail) - Dovetail is a research analysis platform for transcript review and insight generation. It helps teams code interviews, analyze feedback, and create actionable research summaries. - [Dub](https://composio.dev/toolkits/dub) - Dub is a short link management platform with analytics and API access. Use it to easily create, manage, and track branded short links for your business. - [Elasticsearch](https://composio.dev/toolkits/elasticsearch) - Elasticsearch is a distributed, RESTful search and analytics engine for all types of data. It delivers fast, scalable search and powerful analytics across massive datasets. ## Frequently Asked Questions ### 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. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)