Ngrok with Vercel AI SDK

How to integrate Ngrok MCP with Vercel AI SDK v6

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Ngrok with TL;DR What is Vercel AI SDK What is the Ngrok MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Ngrok MCP Agent with another framework Explore Other Toolkits FAQ

Connect Ngrok without Auth hassles

We manage OAuth, API Key, token refresh, and scopes, you just build.

Try for Free

Introduction

This guide walks you through connecting Ngrok to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ngrok agent that can list all active tunnels and endpoints, show https edges currently configured, list all api keys for your account through natural language commands.

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

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

Also integrate Ngrok with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Ngrok integration
Using Composio's Tool Router to dynamically load and access Ngrok 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 Ngrok MCP server, and what's possible with it?

The Ngrok MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ngrok account. It provides structured and secure access to your Ngrok tunnels and API keys, so your agent can perform actions like managing endpoints, listing tunnels, handling API keys, and auditing IP restrictions on your behalf.

Active tunnel and endpoint monitoring: Instantly list all active tunnels and endpoints in your Ngrok account, making it simple to track running services and public URLs.
API key management: Programmatically create, list, and delete API keys to securely manage who and what can access your Ngrok resources.
HTTPS edge configuration visibility: Retrieve a comprehensive list of all HTTPS edges to review and manage how Ngrok handles encrypted traffic.
IP restriction and policy auditing: List and inspect all IP restrictions and policy rules, helping you enforce access control and security best practices.
Detailed access audit trails: Fetch details about specific IP restrictions for security audits and compliance, ensuring you always know who can access your tunnels and APIs.

Supported Tools & Triggers

Tools

Create API KeyCreates a new API key for authenticating with the ngrok API.

Create Tunnel CredentialCreates a new tunnel authtoken credential for authenticating ngrok agents.

Create EndpointCreate a cloud endpoint on the ngrok account.

Create Event SourceAdd a new event source to an event subscription.

Create Event SubscriptionCreates a new event subscription in ngrok.

Create HTTPS EdgeCreates a new HTTPS edge in your ngrok account.

Create HTTPS Edge RouteCreates a new route on an HTTPS edge in ngrok.

Create SSH CredentialCreates a new SSH credential from an uploaded public SSH key.

Create VaultCreates a new vault in your ngrok account.

Create Vault SecretTool to create a new secret in an ngrok vault for secure storage of sensitive data like API keys, passwords, or tokens.

Delete API KeyDelete an API key by its ID.

Delete CredentialsDelete a tunnel authtoken credential by ID.

Delete HTTPS Edge Route Circuit Breaker ModuleDelete the Circuit Breaker module from an HTTPS Edge Route.

Delete Edge Route Compression ModuleDelete the compression module from an HTTPS edge route.

Delete Edge Route Request Headers ModuleDelete the request headers module from an HTTPS edge route.

Delete Edge Route Response Headers ModuleDelete the response headers module from an HTTPS edge route.

Delete Edge Route SAML ModuleDelete the SAML module configuration from an HTTPS edge route.

Delete Edge Route User Agent Filter ModuleDelete the user agent filter module from an HTTPS edge route.

Delete Edge Route Webhook Verification ModuleDelete the webhook verification module from an HTTPS edge route.

Delete Edge Route WebSocket TCP Converter ModuleDelete the WebSocket TCP converter module from an HTTPS edge route.

Delete EndpointDelete an endpoint by ID.

Delete Event SourceDelete an event source from an event subscription.

Delete Event SubscriptionDelete an event subscription by ID.

Delete HTTPS EdgeDelete an HTTPS edge by ID.

Delete HTTPS Edge RouteDelete an HTTPS edge route by ID.

Delete Reserved Domain CertificateDetach the certificate attached to a reserved domain.

Delete Reserved Domain Certificate Management PolicyDetach the certificate management policy from a reserved domain.

Delete SecretDelete a vault secret by ID.

Delete SSH CredentialsDelete an SSH credential by ID.

Delete VaultDelete a vault by ID.

Get API KeyGet the details of an API key by ID.

Get CredentialsTool to retrieve detailed information about a tunnel authtoken credential by ID.

Get Edge Route Backend ModuleRetrieves the backend module configuration for an HTTPS edge route.

Get Edge Route Circuit Breaker ModuleTool to retrieve the circuit breaker module configuration for a specific HTTPS edge route.

Get Edge Route Compression ModuleRetrieves the compression module configuration for a specific HTTPS edge route.

Get Edge Route IP Restriction ModuleRetrieves the IP restriction module configuration for a specific HTTPS edge route.

Get Edge Route OIDC ModuleRetrieves the OIDC (OpenID Connect) module configuration for a specific HTTPS edge route.

Get Edge Route Request Headers ModuleRetrieves the request headers module configuration for a specific HTTPS edge route.

Get Edge Route Response Headers ModuleGet the response headers module configuration for an HTTPS edge route.

Get Edge Route SAML ModuleRetrieves the SAML authentication module configuration for a specific HTTPS edge route.

Get Edge Route Traffic PolicyRetrieves the Traffic Policy module configuration for a specific HTTPS edge route.

Get Edge Route User Agent Filter ModuleRetrieves the user agent filter module configuration for a specific HTTPS edge route.

Get Edge Route Webhook Verification ModuleRetrieves the webhook verification module configuration for an HTTPS edge route.

Get Edge Route WebSocket TCP Converter ModuleRetrieves the WebSocket TCP Converter module configuration for a specific HTTPS edge route.

Get EndpointGet the status of an endpoint by ID.

Get Event SourceGet an event source by type for a specific event subscription.

Get HTTPS EdgeGet the details of an HTTPS edge by ID.

Get HTTPS Edge Mutual TLS ModuleRetrieves the mutual TLS module configuration for an HTTPS edge.

Get HTTPS Edge RouteRetrieves detailed information about a specific HTTPS edge route by its ID.

Get IP Restriction DetailsRetrieves detailed information about a specific IP restriction by its ID.

Get Reserved DomainGet the details of a reserved domain by ID.

Get SecretTool to retrieve detailed information about a vault secret by ID.

Get Secrets by VaultTool to get all secrets in a vault by vault ID.

Get SSH CredentialsTool to retrieve detailed information about an SSH credential by ID.

Get VaultGet the details of a vault by ID.

List Agent IngressesList all Agent Ingresses owned by this account.

List API KeysThis tool lists all API keys owned by the user.

List Bot UsersTool to list all bot users on this ngrok account.

List Certificate AuthoritiesList all certificate authorities on this account.

List Tunnel CredentialsList all tunnel authtoken credentials on the ngrok account.

List All EndpointsList all active endpoints on the ngrok account.

List Event DestinationsList all Event Destinations on the ngrok account.

List Event SubscriptionsList all event subscriptions on the ngrok account.

List Event Subscription SourcesTool to list the types for which this event subscription will trigger.

List Failover BackendsList all failover backends on this account.

List HTTP Response BackendsList all HTTP response backends on the account.

List HTTPS EdgesLists all HTTPS Edges in your ngrok account.

List IP PoliciesList all IP policies on this account.

List IP Policy RulesThis tool lists all IP policy rules associated with your ngrok account.

List IP RestrictionsLists all IP restrictions configured on the ngrok account.

List Reserved AddressesList all reserved addresses on this account.

List Reserved DomainsList all reserved domains on this account.

List Service UsersTool to list all service users on this ngrok account.

List SSH Certificate AuthoritiesList all SSH Certificate Authorities on this account.

List SSH CredentialsList all SSH credentials on the ngrok account.

List SSH Host CertificatesList all SSH Host Certificates issued on this account.

List SSH User CertificatesList all SSH user certificates on the ngrok account.

List Static BackendsList all static backends on the account.

List TCP EdgesLists all TCP Edges in your ngrok account.

List TLS CertificatesList all TLS certificates on the ngrok account.

List TLS EdgesLists all TLS Edges in your ngrok account.

List Active TunnelsList all active tunnels in the ngrok account.

List Tunnel SessionsList all online tunnel sessions running on this account.

List VaultsList all vaults owned by the ngrok account.

List Vault SecretsList all vault secrets owned by the ngrok account.

List Weighted BackendsList all weighted backends on the ngrok account.

Replace Edge Route Circuit Breaker ModuleReplaces the circuit breaker module configuration on an HTTPS edge route.

Replace Edge Route Compression ModuleReplaces the compression module configuration for an HTTPS edge route.

Replace Edge Route Request Headers ModuleReplaces the request headers module configuration for an HTTPS edge route.

Replace Edge Route Response Headers ModuleReplaces the response headers module configuration for an HTTPS edge route.

Replace Edge Route Traffic PolicyReplaces the traffic policy module on an HTTPS edge route.

Replace Edge Route User Agent Filter ModuleReplaces the user agent filter module configuration for an HTTPS edge route.

Replace Edge Route Webhook Verification ModuleReplaces the webhook verification module configuration for an HTTPS edge route.

Update API KeyUpdates attributes of an API key by ID.

Update CredentialsTool to update attributes of a tunnel authtoken credential by ID.

Update EndpointTool to update an Endpoint by ID, currently available only for cloud endpoints.

Update Event SubscriptionTool to update attributes of an event subscription by ID.

Update HTTPS Edge RouteTool to update an HTTPS edge route by ID.

Update Reserved DomainTool to update the attributes of a reserved domain by ID.

Update SecretTool to update a vault secret by ID.

Update SSH CredentialTool to update attributes of an SSH credential by ID.

Update VaultTool to update attributes of a vault by 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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
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: ["ngrok"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Ngrok 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 Ngrok-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 Ngrok 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 ngrok, 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 Ngrok 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 Ngrok 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: ["ngrok"],
  });

  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 ngrok, 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 Ngrok 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 Ngrok MCP Agent with another framework

OpenAI Agents SDK

Use Ngrok MCP with OpenAI Agents SDK

Claude Agent SDK

Use Ngrok MCP with Claude Agent SDK

Claude Code

Use Ngrok MCP with Claude Code

Claude Cowork

Use Ngrok MCP with Claude Cowork

Codex

Use Ngrok MCP with Codex

OpenClaw

Use Ngrok MCP with OpenClaw

Hermes

Use Ngrok MCP with Hermes

CLI

Use Ngrok MCP with CLI

Google ADK

Use Ngrok MCP with Google ADK

LangChain

Use Ngrok MCP with LangChain

Mastra AI

Use Ngrok MCP with Mastra AI

LlamaIndex

Use Ngrok MCP with LlamaIndex

CrewAI

Use Ngrok MCP with CrewAI

Explore Other Toolkits

Supabase

Oauth2Api Key

Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.

Codeinterpreter

No Auth

Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.

GitHub

Oauth2

GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.

TOOLKIT MARKETPLACE

FAQ

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

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

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

Yes, absolutely. You can configure which Ngrok 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 Ngrok data and credentials are handled as safely as possible.

Used by agents from

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 free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

Karan skipped his own birthday party to fix our critical issue. It was 10 pm and he diverted his Waymo to help us instead. This really sets the bar, shows you the commitment you need to have when users rely on your software.

Abhi AryaCo-founder, Opennote

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

We chose Composio over Pipedream because it delivered depth where it mattered. It supported niche tools and tricky edge cases that other platforms simply ignored. Giving us confidence to scale without compromising.

Ryan YuFounder, Extra Thursday

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down in the complexities of managing agent auth would have been a death sentence for Extra Thursday.

Tomisin JenrolaFounder & CEO, SwarmZero

Before partnering with Composio, adding tool integrations was a slow, resource-intensive process. Each integration could take weeks or months of engineering time, and maintaining them meant constantly keeping up with API changes.

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

How to integrate Ngrok MCP with Vercel AI SDK v6

Table of Contents

Connect Ngrok without Auth hassles

Introduction

Also integrate Ngrok with

TL;DR

What is Vercel AI SDK?

What is the Ngrok MCP server, and what's possible with it?

Supported Tools & Triggers

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

Handle user input and stream responses with real-time tool feedback

Complete Code

Conclusion

How to build Ngrok MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Supabase

Codeinterpreter

GitHub

FAQ

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

Can I use Tool Router MCP with Vercel AI SDK v6?

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

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability