How to integrate DeployHQ MCP with Vercel AI SDK v6

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

Introduction

This guide walks you through connecting DeployHQ to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working DeployHQ agent that can trigger a deployment for project x, list all deployments for project y, get status of last deployment through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a DeployHQ account through Composio's DeployHQ 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 DeployHQ integration
  • Using Composio's Tool Router to dynamically load and access DeployHQ 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 DeployHQ MCP server, and what's possible with it?

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

Supported Tools & Triggers

Tools
Delete CommandTool to delete a command from a specified project.
Delete ProjectTool to delete a project from DeployHQ.
Delete Build Cache FileTool to delete an existing build cache file from a project.
Delete Excluded File RuleTool to delete an existing excluded file rule from a project.
Delete Server GroupTool to delete a server group from a project using the DeployHQ API.
Delete TemplateTool to delete a template by its unique permalink.
Get ProjectsTool to retrieve all projects from DeployHQ account.
Get ProjectTool to view an existing project in DeployHQ.
Get Project Build Known HostsTool to list all known hosts within a project using DeployHQ API.
Get Project CommandsTool to retrieve all SSH commands configured for a project.
Get Project Config FilesTool to retrieve a list of all config files in a DeployHQ project.
Get Project DeploymentsTool to retrieve a paginated list of all deployments in a project.
Get Project Excluded FilesTool to list all excluded files within a project template.
Get Config FileTool to view a specific config file in a DeployHQ project.
Get Excluded FileTool to view a specific excluded file in a DeployHQ project.
Get Server GroupTool to view a specific server group in a DeployHQ project.
Get Project RepositoryTool to view repository details for a specific project in DeployHQ.
Get Repository BranchesTool to view all available branches in the connected repository for a project.
Get Repository Commit InfoTool to view detailed information about a specific revision in a project's connected repository.
Get Latest Repository RevisionTool to view the latest remote revision of your repository.
Get Recent Commits and TagsTool to view up to 15 most recent revisions and up to 15 most recent tags in a specific branch.
Get Project Scheduled DeploymentsTool to retrieve all upcoming scheduled deployments for a project.
Get Project Server GroupsTool to retrieve all server groups configured for a project.
Get Project ServersTool to retrieve all servers configured for a project.
Get TemplatesTool to retrieve all templates from DeployHQ account.
Get Public TemplateTool to retrieve a specific public template from DeployHQ.
Get Public TemplatesTool to retrieve publicly available deployment templates from DeployHQ.
Update ProjectTool to update project settings in DeployHQ.
Update Build Cache FileTool to update an existing build cache file in a project.
Update Build CommandTool to update an existing build command in a project.
Update Language VersionTool to update the version of a language in a project's build environment.
Update Project CommandTool to update an existing SSH command in a project.
Update Config FileTool to update an existing config file in a DeployHQ project.
Update Excluded FileTool to update an existing excluded file rule in a project.
Update Project RepositoryTool to update repository configuration for a project in DeployHQ.
Update Server GroupTool to update an existing server group in a DeployHQ project.
Update TemplateTool to update an existing template in DeployHQ.
Create ProjectTool to create a new project in DeployHQ.
Generate AI Deployment OverviewTool to generate an AI-powered deployment overview for a revision range.
Create Build Cache FileTool to create a new build cached file within a project.
Create Build CommandTool to create a new build command for a project in DeployHQ.
Create Project Build Known HostTool to create a new known host in a project using DeployHQ API.
Create SSH CommandTool to create a new SSH command for a project in DeployHQ.
Create Config FileTool to create a new config file in a DeployHQ project.
Create Config File DeploymentTool to create a new config file deployment for a project.
Create Excluded FileTool to add a new excluded file to a project.
Abort DeploymentTool to abort a currently running deployment.
Add Project RepositoryTool to add repository details to a project in DeployHQ.
Create Server GroupTool to create a new server group for automated deployments in a DeployHQ project.
Create ServerTool to create a new server configuration in a DeployHQ project.
Create TemplateTool to create a new template in DeployHQ.
Update Project SettingsTool to update settings of an existing DeployHQ project.
Edit Build Cache FileTool to edit an existing build cache file within a project.
Edit Build CommandTool to edit an existing build command within a template in DeployHQ.
Edit SSH CommandTool to edit an existing SSH command in a DeployHQ project.
Edit Config FileTool to edit an existing config file within a project.
Edit Excluded FileTool to edit an existing excluded file rule within a project.
Update Excluded FileTool to update an existing excluded file rule in a project.
Update Project RepositoryTool to update repository details for an existing project in DeployHQ.
Update Server GroupTool to update a server group in a DeployHQ project using the API.
Edit TemplateTool to edit an existing template in DeployHQ.

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: ["deployhq"],
  });

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

  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 deployhq, 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 DeployHQ 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 DeployHQ MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use DeployHQ MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use DeployHQ MCP with Claude Agent SDK

Google ADK

Google ADK

Use DeployHQ MCP with Google ADK

LangChain

LangChain

Use DeployHQ MCP with LangChain

Mastra AI

Mastra AI

Use DeployHQ MCP with Mastra AI

LlamaIndex

LlamaIndex

Use DeployHQ MCP with LlamaIndex

CrewAI

CrewAI

Use DeployHQ MCP with CrewAI

Claude Code

Claude Code

Use DeployHQ MCP with Claude Code

Codex

Codex

Use DeployHQ MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which DeployHQ 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 DeployHQ 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 call↗Get started for free