How to integrate Agenty 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

Agenty logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Agenty to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Agenty agent that can clone your top-performing agent for news sites, list all your running web scraping agents, create a new agent to monitor product prices through natural language commands.

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

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

Also integrate Agenty with

TL;DR

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

The Agenty MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Agenty account. It provides structured and secure access to your web scraping agents and automation tools, so your agent can perform actions like creating, managing, cloning, and monitoring scraping agents, as well as handling API keys and templates—all on your behalf.

  • Agent creation and configuration: Instantly create new scraping or automation agents, set up their configurations, and optionally auto-start them—all without manual coding.
  • Clone and update agents: Duplicate existing agents to streamline workflows or update agent settings to refine your data extraction processes.
  • Fetch and manage agents: List all active agents in your account, retrieve details for any agent, and organize your entire automation fleet from a single place.
  • Template selection and management: Browse public agent templates or sample agents, making it easy to kickstart new projects or standardize scraping tasks.
  • API key management: Create, download, or delete API keys for secure programmatic access and efficient credential management, keeping your automation environment safe and organized.

Supported Tools & Triggers

Tools
Add List RowsTool to add new rows to a list.
Create AgentCreates a new Agenty agent for web scraping, change detection, crawling, map monitoring, or brand monitoring.
Get Agent TemplatesTool to fetch all public agent templates and sample agents.
Delete Agent by IDTool to delete a single agent by its ID.
Fetch all agentsTool to fetch all active agents under an account.
Get Agent by IDRetrieves complete details of a specific agent including its configuration, input settings, scheduler, and metadata.
Update Agent by IDUpdates an existing agent's configuration, settings, and metadata.
Create API KeyCreates a new API key for programmatic access to the Agenty API.
Delete API key by IDDelete an API key by its unique identifier.
Download API keysTool to download all API keys under an account in CSV format.
Get all API keysTool to retrieve all API keys under an account.
Get API key by IDRetrieves detailed information about a specific API key by its ID.
Reset API key by IDResets (regenerates) the secret value of an existing API key.
Update API key by IDUpdates an existing API key's name and role by its unique identifier.
Capture ScreenshotTool to capture a full-page or visible screenshot of any webpage URL.
Capture Screenshot with OptionsTool to capture webpage screenshots with extensive customization options including full-page capture, image format, quality settings, viewport configuration, and post-processing.
Change API key status by IDToggles the enabled/disabled status of an API key.
Get all connectionsRetrieves all connections from your Agenty account.
Convert URL to PDFTool to convert a webpage URL to a PDF document.
Convert URL to PDF with OptionsTool to convert a URL or raw HTML to PDF with customizable options.
Copy AgentTool to copy an existing agent by its ID, creating a duplicate with optionally a new name.
Create WorkflowCreates a new workflow in Agenty to automate actions based on agent events.
Get dashboard reports and usageTool to fetch account reports like pages used by agent, date, and product.
Delete List Row by IDTool to delete a specific row from a list by its unique identifier.
Delete List Rows by IDsTool to delete specific rows from a list by their IDs.
Delete ProjectTool to delete a project by its ID.
Delete ScheduleTool to delete a schedule for an agent by its agent ID.
Delete Workflow by IDTool to delete a workflow by its ID.
Download Agent ResultTool to download agent results by agent ID in CSV, TSV or JSON format.
Download List RowsTool to download list rows as CSV file.
Download usersTool to download users list in CSV format.
Download workflowsTool to download all workflows in CSV format.
Extract Structured DataTool to auto-extract structured data from a webpage including schema.
Extract Structured Data from URLTool to auto-extract structured data from a webpage URL.
Get Agent ResultTool to get the most recent result data for an agent.
Get all team membersTool to retrieve all team members (users) under an account.
Get URL RedirectsTool to get the complete redirect chain for a URL.
Get Job ResultTool to get the result data from a completed job.
Get list by IDRetrieves detailed information about a specific list by its ID.
Get List Row by IDTool to fetch a specific row by its ID from a list.
Get Page ContentTool to fetch the complete HTML content of any webpage URL.
Get Page Content with OptionsTool to fetch HTML content of a webpage with custom options including ad blocking.
Get Project by IDRetrieves complete details of a specific project by its ID, including name, description, creator information, and timestamps.
Get Redirects with OptionsTool to get the complete redirect chain of a URL with custom navigation options.
Get Agent ScheduleTool to retrieve the schedule configuration for a specific agent.
Get User by IDTool to retrieve detailed information about a user by their ID.
Get Workflow by IDRetrieves complete details of a specific workflow by its ID.
Get agent input by IDRetrieves the input configuration for a specific agent by its ID.
Update Input by Agent IDUpdates the input configuration for a specific agent in Agenty.
Download jobsTool to download all jobs in CSV format.
Download job file by IDTool to download output files by job ID.
Download Job Result by IDTool to download the agent output result by job ID.
Fetch all jobsTool to fetch all jobs under an account.
Get Job by IDRetrieves comprehensive details about a specific job including its status, progress metrics (pages processed/succeeded/failed), timing information (created/started/completed times), resource consumption (page credits), and any error messages.
Get Job Logs by IDTool to fetch logs for a given job by its ID.
List job output filesLists all output files generated by a specific job.
Start Agent JobTool to start a new agent job.
Stop Job by IDTool to stop a running job by job ID.
Clear List RowsTool to clear all rows in a list by its ID.
Create ListTool to create a new list.
Delete List by IDTool to delete a specific list by its ID.
Download listsTool to download all lists in CSV format.
Get all listsTool to retrieve all lists under an account.
Fetch List Rows by IDTool to fetch all rows in a specified list.
Update List by IDTool to update a list's name and optionally description by list ID.
Upload CSV file to ListTool to upload a CSV file to an Agenty list for bulk import of data rows.
Patch WorkflowTool to partially update a workflow by ID.
Add Agents to ProjectAdd one or more agents to an Agenty project to organize and group related agents together.
Create ProjectCreates a new project in Agenty.
Get all projectsRetrieve all projects in the authenticated user's account.
Remove Agent from ProjectRemove an agent from an Agenty project.
Scrape Webpage DataTool to scrape data from any webpage using jQuery/CSS selectors.
Toggle Agent ScheduleTool to toggle schedule on/off for an agent.
Transfer Agent OwnershipTool to transfer agent ownership to another Agenty account.
Update List RowTool to update a specific row in a list by list ID and row ID.
Update ProjectUpdate an existing project's name and description in Agenty.
Update Agent ScheduleUpdates the schedule configuration for a specific agent.
Update User by IDTool to update a user's information by user ID.
Update WorkflowTool to update an existing workflow's configuration by workflow ID.

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: ["agenty"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Agenty 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 Agenty-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 Agenty 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 agenty, 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 Agenty 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 Agenty 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: ["agenty"],
  });

  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 agenty, 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 Agenty 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 Agenty MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Agenty MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Agenty MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Agenty MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Agenty MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Agenty MCP with Claude Cowork

Codex logo

Codex

Use Agenty MCP with Codex

Cursor logo

Cursor

Use Agenty MCP with Cursor

OpenClaw logo

OpenClaw

Use Agenty MCP with OpenClaw

Hermes logo

Hermes

Use Agenty MCP with Hermes

CLI logo

CLI

Use Agenty MCP with CLI

Google ADK logo

Google ADK

Use Agenty MCP with Google ADK

LangChain logo

LangChain

Use Agenty MCP with LangChain

Mastra AI logo

Mastra AI

Use Agenty MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Agenty MCP with LlamaIndex

CrewAI logo

CrewAI

Use Agenty MCP with CrewAI

OpenCode logo

OpenCode

Use Agenty MCP with OpenCode

VS Code logo

VS Code

Use Agenty MCP with VS Code

FAQ

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

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

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

Yes, absolutely. You can configure which Agenty 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 Agenty 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↗