Box logo

Box

Community
hmk

A Box model context protocol server to search, read and access files

Publisherhmk
Repositorybox-mcp-server
LanguageJavaScript
Forks
11
Stars
10
Available tools
0
Transport typestdio
Categories
LicenseBSD-3-Clause
Links
  • Connect tools to AI workflows

    Box exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    10 stars and 11 forks from the linked repository.

box-mcp-server

CI

Usage

You will need:

  • BOX_USER_ID

and one of the following:

  • BOX_JWT_BASE64 (recommended)
  • BOX_JWT_CONFIG_PATH
  • BOX_JWT

Auth

JSON Web Token (JWT) Authorization (recommended)

How to get a JWT

Using a JWT Config allows persistent connection to Box.

You will need a paid Box enterprise account, or you can sign up for a free developer account (make sure you are signed out of Box before clicking that link).

Visit the Box Developer Console and create a new application. Make sure the authorization type is JSON Web Token.

Go to Configuration > Add and Manage Public Keys and Generate a Public/Private Keypair. If you have not already, Box prompt you to set up 2 factor authentication and Authorize the application as an administrator in your box account. You will need to:

  1. give the application App + Enterprise Access, and
  2. enable the make API calls using the as-user header option

via the Box Application's Configuration page. Make sure to reauthorize the application if you are modifying these settings.

Base64 encoding JWT

To encode your JWT in Base64, you can use the following command in your terminal:

sh
cat /path/to/your/box-jwt-config.json | base64

Replace /path/to/your/box-jwt-config.json with the actual path to your JWT configuration file. This will output the Base64 encoded JWT which you can then use in your environment variables.

Claude Desktop Configuration

json
{
  "mcpServers": {
    "box": {
      "command": "npx",
      "args": ["box-mcp-server"],
      "env": {
        "BOX_JWT_BASE64": "YOUR_BASE64_ENCODED_JWT",
        "BOX_USER_ID": "123456"
      }
    }
  }
}

Developer Token Authorization (easiest)

Using a developer token is the easiest way to integrate with Box, but will only last 60 minutes.

To get started, set the BOX_DEV_TOKEN to a Box Developer Token.

Begin by visiting the Box Developer Console and create a new application. The authorization type does not currently matter, as all support Box Developer Token.

Once your application is created, navigate to its configuration setings and click Generate Developer Token.

Claude Desktop Configuration

json
{
  "mcpServers": {
    "box": {
      "command": "npx",
      "args": ["box-mcp-server"],
      "env": {
        "BOX_DEV_TOKEN": "YOUR_DEV_TOKEN_GOES_HERE"
      }
    }
  }
}

Capabilities

  1. Searching files
  2. Reading files
  • PDF
  • Word
  • Others

Development

Prerequisites

Before you begin, ensure you have the following installed:

  • Node.js (recommended v22 or higher)
  • npm
  • git
  • dotenv

Setting up Development Environment

To set up the development environment, follow these steps:

  1. Fork the repository

    • Click the "Fork" button in the top-right corner of this repository
    • This creates your own copy of the repository under your Github acocunt
  2. Clone Your Fork:

    sh
    git clone https://github.com/YOUR_USERNAME/box-mcp-server.git
    cd box-mcp-server
  3. Add Upstream Remote

    sh
    git remote add upstream https://github.com/hmk/box-mcp-server.git
  4. Copy the dotenv file

    sh
    cp .env.template .env
  5. Install dependencies:

    sh
    npm install
  6. Run watch to keep index.js updated:

    sh
    npm run watch
  7. Start the model context protocol development server:

    sh
    dotenv npx @modelcontextprotocol/inspector node PATH_TO_YOUR_CLONED_REPO/dist/index.js
  8. If the development server did not load the environment variable correctly, set the BOX_DEV_TOKEN on the left-hand side of the mcp inspector.

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "box": {
      "command": "npx",
      "args": [
        "box-mcp-server"
      ],
      "env": {
        "BOX_JWT_BASE64": "YOUR_BASE64_ENCODED_JWT",
        "BOX_USER_ID": "123456"
      }
    }
  }
}

Use Box MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Box is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Box as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Box MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "box": {
      "command": "npx",
      "args": [
        "-y",
        "box-mcp-server"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Box MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Box MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Box to help me with this task?
Box
Sure. I read it.
Here is what I found using Box.

Frequently asked questions

What is the Box MCP server used for?

Box is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Box MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Box with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Box MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Box connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Box MCP to TypingMind?

Box runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Box MCP provide in TypingMind?

Box exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Box MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Box requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇