SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Docsbot ai MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Docsbot ai MCP. List all bots for your team, generate support ticket from recent chat, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Docsbot ai logoDocsbot ai
Api Key

Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.

38 Tools

Introduction

This guide walks you through connecting Docsbot ai to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Docsbot ai agent that can create and update bots, add training sources, search bot content, review conversations and leads, and track bot statistics through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

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

The Docsbot ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Docsbot ai account. It provides structured and secure access to your Docsbot ai bots, teams, and conversation data, so your agent can perform actions like creating bots, managing teams, generating support tickets, and analyzing user questions on your behalf.

  • Custom bot creation and management: Instantly create new Docsbot ai bots or update existing ones, letting your agent provision and configure bots for different documentation needs.
  • Team administration and overview: Allow your agent to fetch details about your teams or list all teams associated with your account, making it easier to manage collaboration and bot access.
  • Automated support ticket generation: Easily convert chatbot conversations into structured support tickets, so your agent can help streamline customer support and issue tracking.
  • Bot question and source analytics: Retrieve lists of questions asked to your bots or review all data sources connected to a given bot, empowering your agent to surface insights or monitor bot effectiveness.
  • Seamless bot and data cleanup: Direct your agent to delete bots or manage bot sources, helping you keep your Docsbot ai environment tidy and up to date.

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: ["docsbot_ai"],
  });

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

  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 docsbot_ai, 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 Docsbot ai 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 Docsbot ai action and event your agent gets out of the box.

Capture Conversation Lead

Tool to capture lead information by updating conversation metadata and saving the lead.

Create Bot

Tool to create a new bot within a team.

Create Bot Source

Tool to create a new source for a bot.

Create Webhook

Tool to create a new webhook subscription for a bot.

Delete Bot

Tool to delete a specific bot by its ID.

Delete Conversation

Tool to delete a specific conversation by its ID.

Delete Lead

Tool to delete a specific lead by ID.

Delete Question

Tool to delete a specific question from history.

Delete Source

Tool to delete a specific source from a bot by its ID.

Delete Webhook

Tool to delete a webhook (unsubscribe) by its ID.

Generate Conversation Ticket

Generates a structured support ticket from a Chat Agent conversation.

Get Bot Details

Tool to fetch details of a specific bot by ID within a team.

Get Bot Monthly Reports

Tool to retrieve monthly statistical reports for a bot.

Get Bot Statistics

Tool to retrieve comprehensive statistics and analytics for a bot over a time period or date range.

Get Source Details

Tool to retrieve detailed information about a specific source by its ID.

Get Team Details

Tool to fetch details of a specific team by its ID.

Get Upload URL

Get a presigned upload URL for uploading files as sources.

Get Webhook Details

Tool to retrieve details of a specific webhook by ID.

List Team Bots

List all bots for a given team.

List Bot Conversations

Tool to list conversation history for a bot with pagination.

List Bot Leads

Tool to list captured leads for a bot with pagination and date filtering.

List Questions

Tool to list all questions asked of a specific bot.

List Research Jobs

Tool to list all deep research jobs for a bot with pagination support.

List Bot Sources

Retrieves a paginated list of all sources for a specific bot within a team.

List Team Members

Tool to list all members of a team including their roles.

List Teams

Tool to list all teams.

List Bot Webhooks

List all registered webhooks for a bot.

Rate Answer

Tool to rate an answer from chat APIs as positive (1), neutral (0), or negative (-1).

Refresh Source

Tool to refresh a source to re-index its content.

Semantic Search Bot Content

Tool to perform semantic search on a bot's indexed content.

Test Escalated Webhook

Tool to trigger a test delivery of the conversation.

Test Lead Webhook

Tool to trigger a test lead webhook delivery.

Test Research Webhook

Tool to trigger a deep research webhook delivery test.

Trigger Rated Webhook Test

Tool to trigger a conversation.

Update Bot

Update a bot's configuration settings such as name, description, model, temperature, and appearance.

Update Team

Tool to update specific fields for a team.

Update Webhook

Update a bot webhook's target URL, subscribed events, label, or expiration date.

Upload File to Cloud Storage

Upload a file to cloud storage via a presigned URL.

FRAMEWORKS

How to build Docsbot ai MCP Agent with another framework

Claude Code logo

Claude Code

Use Docsbot ai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Docsbot ai MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Docsbot ai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Docsbot ai MCP with Claude Agent SDK

Codex logo

Codex

Use Docsbot ai MCP with Codex

OpenClaw logo

OpenClaw

Use Docsbot ai MCP with OpenClaw

Hermes logo

Hermes

Use Docsbot ai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Docsbot ai MCP with Atomic Agent

Google ADK logo

Google ADK

Use Docsbot ai MCP with Google ADK

LangChain logo

LangChain

Use Docsbot ai MCP with LangChain

Mastra AI logo

Mastra AI

Use Docsbot ai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Docsbot ai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Docsbot ai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Docsbot ai MCP with Pydantic AI

AutoGen logo

AutoGen

Use Docsbot ai MCP with AutoGen

FAQ

Frequently asked questions

Start with Docsbot ai.It takes 30 seconds.

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

Start building