SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Perplexityai MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Perplexityai MCP. Summarize the latest ai research papers, generate a creative story about space travel, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Perplexityai logoPerplexityai
Api Key

Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.

28 Tools

Introduction

This guide walks you through connecting Perplexityai to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Perplexityai agent that can run chat completions, search the web, create embeddings, execute agents, and check your usage analytics through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Perplexityai with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexKimi CodeGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentCLIGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Perplexity AI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Perplexity AI account. It provides structured and secure access to Perplexity AI's conversational models, web search, embeddings, and agent execution, so your agent can search the web, generate responses, run Perplexity agents, create embeddings, and manage asynchronous chat requests on your behalf.

  • Web search: Have your agent search the web and return relevant results for research, fact-finding, or current topics.
  • Conversational responses: Let the agent use Perplexity Sonar models to answer questions, explain topics, and generate human-like text.
  • Asynchronous chat tasks: Direct your agent to start longer chat requests, check their progress, and review previously submitted requests.
  • Perplexity agent execution: Instruct your agent to run a Perplexity agent for tasks that need an agent-generated response.
  • Text embeddings and model discovery: Have your agent create standard or contextualized embeddings for text and view the Perplexity models available to your account.

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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
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 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
4

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
5

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
6

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: ["perplexityai"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Perplexityai 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 Perplexityai-related tools through the MCP protocol
7

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 Perplexityai tools that the agent can use
8

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 perplexityai, 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
9

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 Perplexityai 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 Perplexityai 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: ["perplexityai"],
  });

  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 perplexityai, 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 Perplexityai 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.
TOOLS

Supported Tools

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

Cancel Agent Response

Request cancellation of an existing durable agent response.

Create Async Chat Completion

Create Async Chat Completion (POST /v1/async/sonar).

Create Chat Completion

Generate a chat-compatible response from conversation messages, with optional search controls.

Create Contextualized Embeddings

Create Contextualized Embeddings (POST /v1/contextualizedembeddings).

CreateEmbeddings

Generate vector embeddings for independent texts (queries, sentences, documents).

Create Orchestrator Chat Completion

Create a non-streaming OpenAI-compatible chat completion using a cataloged Orchestrator model.

Create Orchestrator Message

Create a non-streaming Anthropic-compatible message using an Orchestrator catalog model.

CreateOrchestratorResponse

Generate a non-streaming model response through the Perplexity Orchestrator using a creator/model-name catalog ID, input text or structured items, optional tools, and structured output settings.

Create Skill

Create a Project-owned skill from a ZIP bundle containing SKILL.

Delete Skill

Delete a skill only if its current revision matches expected_revision.

Download Agent Response File

Download a file delivered by an Agent response's share_file tool.

Evaluate Decisions

Evaluate named yes/no, choice, and score questions against shared content.

Execute Agent

Create Agent Response (POST /v1/agent).

Get Agent Response

Retrieve a stored Agent response as a JSON snapshot (GET /v1/agent/{id}).

Get Async Chat Completion

Get Async Chat Completion (GET /v1/async/sonar/{id}).

Get Member Usage Analytics

Get organization Perplexity usage per member in daily UTC buckets.

Get Orchestrator Model

Retrieve one Orchestrator model by its full provider/model id.

Get Skill

Get a skill's metadata by identifier, optionally at a specific revision.

Get Skill Download URL

Get a short-lived URL to download a skill bundle as a ZIP, optionally for a specific revision; omit the revision to select the active revision.

Get Usage Analytics

Get an organization's Perplexity Computer usage as a bucketed time series.

List Agent Response Files

List files an agent response delivered from its sandbox using share_file.

List Async Chat Completions

List a page of legacy asynchronous Sonar chat completion requests for the authenticated user, including their statuses.

List Models

List Models (GET /v1/models).

List Orchestrator Models

List available Orchestrator API models sorted by id, with base token prices.

List Skill Revisions

List a skill's revisions, newest first.

List Skills

List skills in the authenticated Project, newest first.

Perplexity Search (Raw Results)

Search the Web (POST /search).

Update Skill

Upload a new ZIP bundle as a revision of an existing Project-owned skill.

FRAMEWORKS

How to build Perplexityai MCP Agent with another framework

Claude Code logo

Claude Code

Use Perplexityai MCP with Claude Code

Cursor logo

Cursor

Use Perplexityai MCP with Cursor

ChatGPT logo

ChatGPT

Use Perplexityai MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Perplexityai MCP with Claude Cowork

Antigravity logo

Antigravity

Use Perplexityai MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Perplexityai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Perplexityai MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Perplexityai MCP with Grok Bot

Muse logo

Muse

Use Perplexityai MCP with Muse

Codex logo

Codex

Use Perplexityai MCP with Codex

Kimi Code logo

Kimi Code

Use Perplexityai MCP with Kimi Code

Grok Build logo

Grok Build

Use Perplexityai MCP with Grok Build

VS Code logo

VS Code

Use Perplexityai MCP with VS Code

OpenCode logo

OpenCode

Use Perplexityai MCP with OpenCode

OpenClaw logo

OpenClaw

Use Perplexityai MCP with OpenClaw

Hermes logo

Hermes

Use Perplexityai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Perplexityai MCP with Atomic Agent

CLI logo

CLI

Use Perplexityai MCP with CLI

Google ADK logo

Google ADK

Use Perplexityai MCP with Google ADK

LangChain logo

LangChain

Use Perplexityai MCP with LangChain

Mastra AI logo

Mastra AI

Use Perplexityai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Perplexityai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Perplexityai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Perplexityai MCP with Pydantic AI

AutoGen logo

AutoGen

Use Perplexityai MCP with AutoGen

FAQ

Frequently asked questions

Start with Perplexityai.It takes 30 seconds.

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

Start building