SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ably MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Ably MCP. List all active channels and their details, get message history from 'support-chat' channel, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ably logoAbly
Api Key

Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.

25 Tools

Introduction

This guide walks you through connecting Ably to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ably agent that can publish messages to channels, read channel history and presence, send push notifications, manage push devices, and check app stats through natural language commands.

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

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

Also integrate Ably 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 Ably integration
  • Using Composio's Tool Router to dynamically load and access Ably 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 Ably MCP server, and what's possible with it?

The Ably MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ably account. It provides structured and secure access to your channels, messages, presence data, application statistics, and push notifications, so your agent can publish messages, inspect active channels, review channel history, monitor presence, and manage push notifications on your behalf.

  • Channel messaging: Have your agent publish a message to one channel or send batches of messages across multiple channels.
  • Channel activity and history: Let the agent list active channels, retrieve channel details, review message history, and inspect earlier versions of a message.
  • Presence monitoring: Direct your agent to check who is currently present in one or more channels and review past presence activity.
  • Push notification management: Instruct your agent to send individual or batch push notifications, manage channel subscriptions, and register, update, inspect, or unregister receiving devices.
  • Application insights: Have your agent retrieve Ably service time and review application usage statistics.

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: ["ably"],
  });

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

  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 ably, 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 Ably 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 Ably action and event your agent gets out of the box.

Query Batch Presence

Queries the presence states of multiple Ably channels in a single request, retrieving member presence details for the specified channels.

Query Batch Presence History

Query presence history for multiple Ably channels, with optional start and end times and forwards or backwards ordering.

Delete Channel Subscription

Unsubscribes a device or client from push notifications for a specified channel, or across all channels if no channel is provided.

Get Channel Details

Retrieves status and occupancy metadata for a specific Ably channel, including connection, presence, publisher, and subscriber metrics.

Get Channel History

Retrieves a page of message history for a specified Ably channel, with time range, limit, and direction filters.

Get Channel Presence

Tool to obtain the set of members currently present for a channel.

Get Message Versions

Retrieves a page of historical versions of a specific Ably channel message, including the original and subsequent updates or deletes.

Get Channel Presence History

This tool retrieves the history of presence messages for a specified channel in Ably.

Get Push Device Registration

Retrieves a device's push registration by device ID, including available platform, state, recipient, and metadata fields.

Get Ably Service Time

This tool retrieves the current server time from Ably's service in milliseconds since the epoch.

Get Application Stats

Retrieve a page of Ably application usage statistics by minute, hour, day or month, with optional time range, direction and limit.

List Channels

Tool to enumerate all active channels in the Ably application.

List Push Channels

Lists a page of Ably channels with at least one subscribed device for push notifications.

List Push Channel Subscriptions

Lists a page of push channel subscriptions filtered by channel, client ID, or device ID, with pagination links; at least one filter is required.

List Registered Push Devices

List a page of Ably push device registrations, optionally filtered by device ID or client ID.

Patch Push Device Registration

Partially update an existing Ably push device registration.

Batch Publish Messages

Tool to batch publish messages to multiple channels in parallel.

Publish Message to Channel

Publishes a message to a specified Ably channel with a string or JSON object payload and an optional event name and client ID.

Publish Push Notification

Tool to publish a push notification directly to device(s) via Ably's Push Notifications API.

Batch Publish Push Notifications

Tool to batch publish push notifications directly to specific recipients.

Register Push Device

Register an iOS, Android, or browser device with Ably to receive push notifications.

Request Access Token

Request an Ably access token with optional capabilities, client ID and lifetime.

Unregister All Push Devices

Unregister matching Ably push devices, optionally filtering by device ID or client ID, but not both.

Unregister Push Device

Unregister a single Ably push device by device ID.

Update Push Device Registration

Upsert an Ably push device registration, creating it or replacing an existing registration.

FRAMEWORKS

How to build Ably MCP Agent with another framework

Claude Code logo

Claude Code

Use Ably MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ably MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ably MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ably MCP with Claude Agent SDK

Codex logo

Codex

Use Ably MCP with Codex

OpenClaw logo

OpenClaw

Use Ably MCP with OpenClaw

Hermes logo

Hermes

Use Ably MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ably MCP with Atomic Agent

Google ADK logo

Google ADK

Use Ably MCP with Google ADK

LangChain logo

LangChain

Use Ably MCP with LangChain

Mastra AI logo

Mastra AI

Use Ably MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ably MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ably MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Ably MCP with Pydantic AI

AutoGen logo

AutoGen

Use Ably MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Ably.It takes 30 seconds.

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

Start building