SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Templated MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Templated MCP. Generate invoice pdf from customer data, list all available image templates, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Templated logoTemplated
Api Key

Templated is a platform for designing templates and automating the creation of images and PDFs via API. It lets you dynamically generate branded content and documents at scale.

30 Tools

Introduction

This guide walks you through connecting Templated to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Templated agent that can generate images and PDFs from templates, create and clone templates, organize folders, tag templates, and merge renders through natural language commands.

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

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

Also integrate Templated with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Templated MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Templated account. It provides structured and secure access to your templates and renders, so your agent can generate dynamic documents, manage templates, clone or tag designs, and retrieve render results on your behalf.

  • Automated document and image generation: Instantly have your agent render PDFs or images from any saved template, filling in dynamic variables to create invoices, certificates, or marketing materials.
  • Template management and organization: Let your agent list, retrieve, clone, or delete templates, keeping your template library organized and up-to-date without manual effort.
  • Dynamic tagging and categorization: Easily add or remove tags from templates, enabling smarter organization and fast searching for specific designs or document types.
  • Render tracking and retrieval: Ask your agent to list all renders for a template or fetch detailed information about a specific document render, making it simple to track document creation and usage history.
  • Account insights and validation: Have your agent retrieve account information to confirm API access, check account metadata, or audit usage details as needed.

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: ["templated"],
  });

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

  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 templated, 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 Templated 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 Templated action and event your agent gets out of the box.

Add Tags to Template

Tool to append new tags to an existing template without overwriting existing tags.

Clone Template

Tool to clone an existing template.

Count Template Clones

Tool to get the count of cloned templates for a specific source template.

Create Folder

Tool to create a new folder for organizing templates and renders.

Create Template Render

Create document renders from templates.

Create Template

Tool to create a new template with specified dimensions and layers.

Delete Folder

Tool to delete a folder by its ID.

Delete Render

Tool to delete a specific render by its ID.

Delete Template

Tool to delete a template by its unique ID.

Duplicate Template Render

Tool to duplicate an existing render with the same settings and template.

Get Account Information

Tool to retrieve account information, including email, name, team name, API usage statistics, and subscription plan.

List All Templates

Tool to list all templates of a user.

List Folder Renders

List renders in a specified folder by ID, with optional pagination.

List Folders

List folders in the account, with optional name filtering and pagination.

List Folder Templates

List templates in a specified folder with optional pagination.

List Fonts

Tool to list all available fonts including Google Fonts and user-uploaded custom fonts.

List Gallery Templates

Tool to list templates from the public gallery.

List All Renders

List renders in the account with optional pagination.

List Template Clones

List cloned templates in the account with optional pagination and filtering by source template ID or external ID.

List Template Renders

List renders for a specified template by ID, with optional pagination.

List Uploads

List uploaded images in the account with optional search, tag filtering and pagination.

Merge Template Renders

Tool to merge multiple renders into a single PDF output.

Move Render to Folder

Tool to move a render to a specific folder.

Move Template to Folder

Tool to move a template to a folder.

Remove Template Tags

Tool to remove specific tags from a template.

Retrieve Template Render

Tool to retrieve details of a specific render by its ID.

Retrieve Template

Tool to retrieve a single Template by its unique ID.

Update Folder

Update the name of an existing folder by its ID.

Update Template

Tool to update an existing template including its properties and layers.

Update Template Tags

Tool to overwrite all tags on a template.

FRAMEWORKS

How to build Templated MCP Agent with another framework

Claude Code logo

Claude Code

Use Templated MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Templated MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Templated MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Templated MCP with Claude Agent SDK

Codex logo

Codex

Use Templated MCP with Codex

OpenClaw logo

OpenClaw

Use Templated MCP with OpenClaw

Hermes logo

Hermes

Use Templated MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Templated MCP with Atomic Agent

Google ADK logo

Google ADK

Use Templated MCP with Google ADK

LangChain logo

LangChain

Use Templated MCP with LangChain

Mastra AI logo

Mastra AI

Use Templated MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Templated MCP with LlamaIndex

CrewAI logo

CrewAI

Use Templated MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Templated MCP with Pydantic AI

AutoGen logo

AutoGen

Use Templated MCP with AutoGen

FAQ

Frequently asked questions

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

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 Templated tools.

Yes, absolutely. You can configure which Templated 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.

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 Templated data and credentials are handled as safely as possible.

Start with Templated.It takes 30 seconds.

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

Start building