How to integrate Persona MCP with Vercel AI SDK v6

GET STARTED FOR FREE
Framework Integration Gradient
Persona Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Persona to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Persona agent that can get all pending verification cases, trigger a new kyc verification for user, list users who failed identity checks through natural language commands.

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

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

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Persona integration
  • Using Composio's Tool Router to dynamically load and access Persona 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 Persona MCP server, and what's possible with it?

The Persona MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Persona account. It provides structured and secure access so your agent can perform Persona operations on your behalf.

Supported Tools & Triggers

Tools
Add Tag to AccountTool to add a tag to an Account in Persona.
Archive Browser Fingerprint List ItemTool to archive a browser fingerprint list item in Persona.
Archive Country List ItemTool to archive a Country List Item by ID.
Archive a Geolocation List ItemTool to archive a geolocation list item from Persona.
Archive Government ID Number List ItemTool to archive a Government ID Number List Item.
Archive a Name List ItemTool to archive a name list item in Persona.
Archive a webhookTool to archive a Persona webhook by its ID.
Archive Email Address List ItemTool to archive an Email Address List Item in Persona.
Archive IP Address List ItemTool to archive an IP address list item in Persona.
Archive Phone Number List ItemTool to archive a phone number list item in Persona.
Archive String List ItemTool to archive a String List Item in Persona.
Clone WebhookTool to clone an existing Persona webhook.
Consolidate AccountsTool to consolidate multiple source accounts into a single destination account.
Create an AccountTool to create an account in Persona.
Create IP Address List ItemTool to create an IP Address List Item in Persona.
Create Country List ItemTool to create a country list item in Persona.
Create Generic DocumentTool to create a generic document in Persona.
Create Email Address List ItemTool to create an email address list item in Persona.
Create Government ID Number List ItemTool to create a new government ID number list item in Persona.
Create Name List ItemTool to create a new name list item in Persona.
Create Phone Number List ItemTool to create a phone number list item in Persona.
Create String List ItemTool to create a String List Item in Persona.
Create WebhookTool to create a new webhook in Persona.
Disable WebhookTool to disable a webhook in Persona.
Enable WebhookTool to enable a webhook in Persona.
Expire Inquiry SessionsTool to expire all inquiry sessions for specified inquiry IDs.
Import Email Address ListsTool to import email addresses into a list from a CSV file.
Import IP Address ListsTool to import IP address lists into Persona.
Import Name ListsTool to import name lists to Persona.
Import Phone Number ListsTool to import phone number lists into Persona.
List All AccountsTool to list all accounts in Persona.
List All API LogsTool to list all API logs in Persona.
List All CasesTool to list all cases in Persona.
List All DevicesTool to list all devices filtered by inquiry session ID.
List all EventsTool to list all events from Persona.
List all ImportersTool to list all importers in Persona.
List All InquiriesTool to list all inquiries in Persona.
List All Inquiry SessionsTool to list all inquiry sessions in Persona.
List All ListsTool to list all lists in Persona.
List All Rate LimitsTool to list all rate limits in Persona.
List All ReportsTool to list all reports in Persona.
List All TransactionsTool to list all transactions in Persona.
List All WebhooksTool to list all webhooks in Persona.
List all Workflow RunsTool to list all workflow runs in Persona.
Redact an AccountTool to permanently redact an account in Persona.
Remove Account TagTool to remove a tag from a Persona Account.
Retrieve a Country List ItemTool to retrieve a country list item by ID in Persona.
Retrieve a Geolocation List ItemTool to retrieve a geolocation list item from Persona.
Retrieve an AccountTool to retrieve an account in Persona.
Retrieve a Name List ItemTool to retrieve a Name List Item in Persona.
Retrieve an EventTool to retrieve an event in Persona.
Retrieve an ImporterTool to retrieve a specific importer in Persona.
Retrieve IP Address List ItemTool to retrieve an IP Address List Item in Persona.
Retrieve an API LogTool to retrieve an API log in Persona.
Retrieve a String List ItemTool to retrieve a string list item by ID in Persona.
Retrieve a WebhookTool to retrieve a webhook by its ID.
Retrieve Browser Fingerprint List ItemTool to retrieve a browser fingerprint list item in Persona.
Retrieve a DocumentTool to retrieve a document from Persona.
Retrieve Generic DocumentTool to retrieve a generic document in Persona.
Retrieve Email Address List ItemTool to retrieve an Email Address List Item in Persona.
Retrieve Government ID Number List ItemTool to retrieve a Government ID Number List Item in Persona.
Retrieve Phone Number List ItemTool to retrieve a phone number list item in Persona.
Rotate Webhook SecretTool to rotate a webhook's secret in Persona.
Search AccountsTool to search accounts in Persona using flexible query criteria.
Search CasesTool to search cases in Persona using advanced query filters with boolean logic.
Set Tags on AccountTool to set tags on a Persona Account.
Update an AccountTool to update an account in Persona.
Update a WebhookTool to update a webhook in Persona.
Update Generic DocumentTool to update a generic document in Persona.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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: ["persona"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Persona 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 Persona-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 Persona 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 persona, 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("\nšŸ‘‹ 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 Persona 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 Persona 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: ["persona"],
  });

  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 persona, 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("\nšŸ‘‹ Session ended.");
    process.exit(0);
  });
}

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

Conclusion

You've successfully built a Persona 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 Persona MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Persona MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Persona MCP with Claude Agent SDK

Google ADK

Google ADK

Use Persona MCP with Google ADK

LangChain

LangChain

Use Persona MCP with LangChain

Mastra AI

Mastra AI

Use Persona MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Persona MCP with LlamaIndex

CrewAI

CrewAI

Use Persona MCP with CrewAI

Claude Code

Claude Code

Use Persona MCP with Claude Code

Codex

Codex

Use Persona MCP with Codex

FAQ

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

With a standalone Persona MCP server, the agents and LLMs can only access a fixed set of Persona tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Persona 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 Persona tools.

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

Yes, absolutely. You can configure which Persona 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 Persona 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.

Book a callā†—Get started for free