SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Chatwork MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Chatwork MCP. List all unread messages across rooms, upload meeting notes file to project room, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Chatwork logoChatwork
Api Key

Chatwork is a team communication platform with group chats, file sharing, and task management. It helps businesses boost collaboration and streamline productivity.

30 Tools

Introduction

This guide walks you through connecting Chatwork to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Chatwork agent that can post and update messages, create rooms, manage tasks, upload files, and manage room members through natural language commands.

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

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

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

The Chatwork MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Chatwork account. It provides structured and secure access to your chats, contacts, files, and rooms, so your agent can perform actions like sending messages, managing tasks, retrieving files, and organizing team communications on your behalf.

  • Room and member management: Easily fetch all chat rooms, list members in any room, and keep your workspace organized by letting your agent handle the heavy lifting.
  • Smart message retrieval and deletion: Have your agent pull recent messages from any chat, search for important info, or even delete specific messages when needed.
  • File sharing and retrieval: Seamlessly upload files to any Chatwork room or retrieve details and download links for files already shared, making document collaboration a breeze.
  • Contact and status insights: Instantly get a list of all your Chatwork contacts or check your current unread messages and task status without switching tabs.
  • Automated task and notification workflows: Let your agent monitor unread messages, mentions, and tasks, helping you stay on top of communication and never miss an important update.

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: ["chatwork"],
  });

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

  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 chatwork, 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 Chatwork 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 Chatwork action and event your agent gets out of the box.

Create Chatwork Room

Tool to create a new group chat room in Chatwork.

Create Room Invitation Link

Creates an invitation link for a Chatwork room using a supplied link code, with optional description and approval settings.

Create Task in Chatwork Room

Tool to create a new task in a Chatwork room.

Delete Message

This tool allows you to delete a specific message from a Chatwork room by calling the DELETE endpoint at https://api.

Delete or Leave Chatwork Room

Tool to leave or delete a Chatwork room.

Delete Room Link

Delete the invitation link for a Chatwork room.

Get Chatwork Contacts

This tool retrieves a list of all contacts from Chatwork.

Get Chatwork File Information

Tool to get information about a specific file in a chat room.

Get Incoming Contact Requests

Tool to retrieve pending contact approval requests received by the authenticated user.

Get My Chatwork Profile

Tool to retrieve the authenticated user's profile information including account details, organization, contact information, and avatar URL.

Get Message

Tool to retrieve information about a specific message in a Chatwork room.

Get My Chatwork Status

This tool retrieves the current status of the authenticated user, including unread message counts and task status.

Get My Chatwork Tasks

Tool to retrieve the authenticated user's task list from Chatwork (up to 100 items).

Get Chatwork Room

Retrieves detailed information about a specific Chatwork room using the API endpoint GET /rooms/{room_id}.

Get Room Files

Tool to get list of files in a chat room (up to 100 files).

Get Room Invitation Link

Retrieves the invitation link for a specified Chatwork room using the API endpoint GET /rooms/{room_id}/link.

Get Room Members

Retrieves a complete list of all members in a specified Chatwork room using the API endpoint GET /rooms/{room_id}/members.

Get Room Messages V2

Tool to retrieve messages from a Chatwork room (up to 100 messages).

Get Chatwork Rooms

Tool to retrieve a list of all chat rooms the authenticated user belongs to.

Get Room Tasks

Retrieves a list of tasks from a Chatwork room.

Get Task

Retrieves detailed information about a specific task in a Chatwork room using the API endpoint GET /rooms/{room_id}/tasks/{task_id}.

Mark Messages as Read

Tool to mark messages as read in a Chatwork room.

Mark Messages as Unread

Tool to mark messages as unread in a Chatwork room.

Post Message

Tool to post a new message to a Chatwork room.

Update Message

Tool to update an existing message in a Chatwork room.

Update Chatwork Room

Tool to update chat room information (name, icon, description).

Update Room Invitation Link

Tool to update the invitation link settings for a Chatwork room.

Update Room Members

Updates the complete member list of a Chatwork room with bulk assignment of member roles (admin, member, readonly).

Update Task Status

Tool to update the completion status of a task in a Chatwork room.

Upload File to Chatwork Room

This tool allows users to upload files to a specific Chatwork room.

FRAMEWORKS

How to build Chatwork MCP Agent with another framework

Claude Code logo

Claude Code

Use Chatwork MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Chatwork MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Chatwork MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Chatwork MCP with Claude Agent SDK

Codex logo

Codex

Use Chatwork MCP with Codex

OpenClaw logo

OpenClaw

Use Chatwork MCP with OpenClaw

Hermes logo

Hermes

Use Chatwork MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Chatwork MCP with Atomic Agent

Google ADK logo

Google ADK

Use Chatwork MCP with Google ADK

LangChain logo

LangChain

Use Chatwork MCP with LangChain

Mastra AI logo

Mastra AI

Use Chatwork MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Chatwork MCP with LlamaIndex

CrewAI logo

CrewAI

Use Chatwork MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Chatwork MCP with Pydantic AI

AutoGen logo

AutoGen

Use Chatwork MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Chatwork.It takes 30 seconds.

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

Start building