SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Egnyte MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Egnyte MCP. List all files in your egnyte projects folder, share the latest contract with the legal team, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Egnyte logoEgnyte
Oauth2

Egnyte is a cloud-based platform for secure file sharing, storage, and governance. It helps teams collaborate efficiently while maintaining data compliance and security.

60 Tools

Introduction

This guide walks you through connecting Egnyte to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Egnyte agent that can list all files in your egnyte projects folder, share the latest contract with the legal team, search egnyte for documents about q2 planning through natural language commands.

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

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

Also integrate Egnyte with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Egnyte integration
  • Using Composio's Tool Router to dynamically load and access Egnyte 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 Egnyte MCP server, and what's possible with it?

The Egnyte MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Egnyte account. It provides structured and secure access to your files, folders, shared links, users, groups, notes, and metadata, so your agent can search content, manage files, create shared links, organize users and groups, and review account information on your behalf.

  • File search and retrieval: Instruct your agent to search files using metadata filters, inspect file or folder details, and download the content you need.
  • File uploads and updates: Have your agent upload a new file or update an existing file at a chosen location in Egnyte.
  • Secure content sharing: Let the agent create shared links for files or folders with access and expiration settings, list existing links, and review your domain's sharing rules.
  • User and group administration: Direct your agent to create users or groups, add group members, list people and groups, and retrieve user details.
  • Content governance and cleanup: Have your agent review file metadata, remove metadata namespaces, or delete notes and comments that are no longer needed.

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: ["egnyte"],
  });

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

  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 egnyte, 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 Egnyte 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 Egnyte action and event your agent gets out of the box.

Create Permissions Audit Report

Tool to generate a permissions audit report for specified date range and filters.

Create user audit report

Tool to create a user audit report in Egnyte.

Create Bookmark

Tool to create a bookmark on a folder using either path or folder_id.

Create Comment

Tool to create a new comment/note on a file in Egnyte.

Create File Audit Report

Tool to generate a file activity audit report for specified date range and filters.

Create Group

Tool to create a new group with display name and members.

Create Shared Link

Tool to create a shared link for a file or folder with accessibility and expiration settings.

Create Login Audit Report

Tool to generate a login audit report for specified date range and filters.

Create User

Tool to create a new user in the Egnyte domain.

Delete Audit Report

Tool to delete an audit report from Egnyte.

Delete Bookmark

Tool to delete a bookmark from the user's bookmarks.

Delete File By ID

Delete a file using persistent file ID.

Delete file or folder

Tool to delete a file or folder at the specified path.

Delete Group

Tool to delete a group from the Egnyte domain.

Delete Shared Link

Tool to delete a shared link by its ID.

Delete Metadata Key

Tool to delete a metadata key from a namespace.

Delete Metadata Namespace

Tool to delete a metadata namespace.

Delete Note

Tool to delete a note/comment in Egnyte by its UUID.

Delete User

Tool to delete a user from the Egnyte domain using the SCIM-compliant endpoint.

Download File

Tool to download file content from a specified path in Egnyte.

Download File By ID

Tool to download file content using persistent file ID from Egnyte.

Get Audit Report

Tool to retrieve an audit report by type and ID.

Get audit job status

Tool to check the status of an audit report generation job.

Get Audit Stream

Tool to stream audit events starting from a specific date.

Get Bookmark

Tool to retrieve details for a specific bookmark by its ID.

Get Events Cursor

Tool to get the latest event cursor position for starting event polling.

Get Events V2

Tool to poll for events (v2) including permission_change event type in addition to file_system and note types.

Get File Metadata by ID

Tool to retrieve file metadata using persistent file ID (group_id) instead of path.

Get file or folder metadata

Tool to get file or folder metadata from Egnyte.

Get File Metadata Values

Tool to retrieve custom metadata values for a file or file version within a specific namespace.

Get Folder By ID

Tool to get folder metadata using a persistent folder ID instead of a path.

Get Folder Statistics

Tool to get statistics for a folder by ID including file counts, folder counts, and size information.

Get Group Details

Tool to retrieve details for a specific group including members and attributes.

Get Link Details

Tool to get detailed information about a shared link by its ID.

Get Link Settings

Tool to retrieve domain link settings including default expiration and allowed link types.

Get Folder Permissions

Tool to get effective permissions for a folder including users and groups with their permission levels.

Get User by ID

Tool to retrieve details for a single user by ID.

Get User Info

Tool to get information about the currently authenticated user.

List Bookmarks

Tool to list all bookmarked folders for the authenticated user with pagination support.

List Comments

Tool to list all comments/notes on a file in Egnyte.

List Groups

Tool to list all custom groups in the Egnyte domain.

List Insights Files

Tool to list recently accessed files for the authenticated user.

List Links V2

Tool to list all shared links using the v2 API with extended response fields.

List Metadata Namespaces

Tool to list all custom metadata keys in a namespace.

List Users

Tool to retrieve all users or a filtered subset from the Egnyte domain.

List workflows

Tool to list all workflows in Egnyte.

List Workflow Tasks

Tool to list all workflow tasks.

Lock File

Tool to lock a file to prevent edits by other users.

Replace Group (PUT)

Tool to fully replace a group's attributes including display name and members.

Advanced Search with Metadata Filters

Tool to perform advanced search with custom metadata filtering in Egnyte using v2 API.

Set File Metadata Values

Tool to set custom metadata values for a file or file version within a specific namespace.

Set Folder Metadata Values

Tool to set custom metadata values for a folder within a namespace.

Set Folder Permissions

Tool to set folder permissions for users or groups.

Stream Audit Events

Tool to stream audit events with filtering by audit types (FILE_AUDIT, LOGIN_AUDIT, PERMISSION_AUDIT).

Update Folder Options

Tool to update folder options including description and other settings.

Update Group

Tool to update specific attributes of a group including display name and members.

Update Metadata Key

Tool to update key definitions including display name, help text, data values for enums, and priority.

Update Metadata Namespace

Tool to update key definitions of a metadata namespace.

Update User

Tool to update specific attributes of a user in the Egnyte domain using the SCIM-compliant endpoint.

Upload File

Tool to upload or update a file at the specified path in Egnyte.

FRAMEWORKS

How to build Egnyte MCP Agent with another framework

Claude Code logo

Claude Code

Use Egnyte MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Egnyte MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Egnyte MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Egnyte MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Egnyte MCP with Grok Bot

Codex logo

Codex

Use Egnyte MCP with Codex

OpenClaw logo

OpenClaw

Use Egnyte MCP with OpenClaw

Hermes logo

Hermes

Use Egnyte MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Egnyte MCP with Atomic Agent

Google ADK logo

Google ADK

Use Egnyte MCP with Google ADK

LangChain logo

LangChain

Use Egnyte MCP with LangChain

Mastra AI logo

Mastra AI

Use Egnyte MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Egnyte MCP with LlamaIndex

CrewAI logo

CrewAI

Use Egnyte MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Egnyte MCP with Pydantic AI

AutoGen logo

AutoGen

Use Egnyte MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Egnyte.It takes 30 seconds.

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

Start building