box-mcp-server

box-mcp-server

Expose your Box files to AI with a Model Context Protocol server.

View on GitHub
10
Stars
11
Forks
10
Watchers
2
Issues
box-mcp-server lets users connect their Box accounts to AI applications via the Model Context Protocol (MCP). It securely authenticates to Box with enterprise credentials or developer tokens and serves file search and reading capabilities to downstream clients. Designed for use with Claude Desktop and the MCP Inspector, it provides seamless integration of Box documents into AI workflows.

Key Features

Box cloud storage integration
JWT and developer token authentication
Secure file access
Search Box files
Read PDF files
Read Word documents
MCP (Model Context Protocol) server implementation
Environment variable configuration
Support for Claude Desktop integration
Development with Node.js

Use Cases

Enabling AI models to access enterprise Box documents
Automating document search and retrieval for knowledge-intensive tasks
Supplying relevant PDFs from Box as context for generative models
Connecting document management systems to AI workflows
Building custom AI-powered assistants for document analysis
Integrating Box storage into Claude Desktop via MCP
Automating review of contracts and reports stored in Box
Supporting research workflows by surfacing relevant files
Facilitating secure AI access to business documentation
Enabling developers to build context-aware AI tools using Box data

README

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.

Star History

Star History Chart

Repository Owner

hmk
hmk

User

Repository Details

Language JavaScript
Default Branch main
Size 220 KB
Contributors 2
License BSD 3-Clause "New" or "Revised" License
MCP Verified Nov 12, 2025

Programming Languages

JavaScript
78.47%
TypeScript
21.53%

Tags

authentication

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • MCP Zotero

    MCP Zotero

    Model Context Protocol server for seamless Zotero integration with AI tools.

    MCP Zotero provides a Model Context Protocol server enabling AI models such as Claude to access and interact with Zotero libraries. Users can securely link their Zotero accounts and perform actions including listing collections, retrieving papers, searching the library, and getting details about specific items. Integration is designed for both standalone operation and as an extension for tools like Claude Desktop.

    • ⭐ 137
    • MCP
    • kaliaboi/mcp-zotero
  • Stape MCP Server

    Stape MCP Server

    An MCP server implementation for integrating Stape with AI model context protocols.

    Stape MCP Server provides an implementation of the Model Context Protocol server tailored for the Stape platform. It enables secure and standardized access to model context capabilities, allowing integration with tools such as Claude Desktop and Cursor AI. Users can easily configure and authenticate MCP connections using provided configuration samples, while managing context and credentials securely. The server is open source and maintained by the Stape Team under the Apache 2.0 license.

    • ⭐ 4
    • MCP
    • stape-io/stape-mcp-server
  • MCP Miro Server

    MCP Miro Server

    Miro board integration for AI assistants via Model Context Protocol.

    MCP Miro Server provides a standardized MCP server interface to the Miro platform, enabling AI assistants to access and manage Miro boards programmatically. It supports a wide range of board and item operations, including creating, listing, updating, and deleting boards and their contents. Secure OAuth token access ensures integration with users’ Miro accounts. Designed to work seamlessly with AI tools like Claude Desktop, it allows efficient and automated Miro workspace management.

    • ⭐ 57
    • MCP
    • k-jarzyna/mcp-miro
  • Azure DevOps MCP Server

    Azure DevOps MCP Server

    Standardized AI access to Azure DevOps via Model Context Protocol.

    Implements the Model Context Protocol (MCP) to enable AI assistants to securely and efficiently interact with Azure DevOps resources. Provides a standardized bridge for managing projects, work items, repositories, pull requests, and pipelines through natural language interfaces. Supports modular authentication and a feature-based architecture for scalability and integration. Facilitates seamless integration with AI tools such as Claude Desktop and Cursor AI.

    • ⭐ 306
    • MCP
    • Tiberriver256/mcp-server-azure-devops
  • Yuque-MCP-Server

    Yuque-MCP-Server

    Seamless integration of Yuque knowledge base with Model-Context-Protocol for AI model context management.

    Yuque-MCP-Server provides an MCP-compatible server for interacting with the Yuque knowledge base platform. It enables AI models to retrieve, manage, and analyze Yuque documents and user information through a standardized Model-Context-Protocol interface. The server supports operations such as document creation, reading, updating, deletion, advanced search, and team statistics retrieval, making it ideal for AI-powered workflows. Inspired by Figma-Context-MCP, it facilitates contextual awareness and dynamic knowledge management for AI applications.

    • ⭐ 31
    • MCP
    • HenryHaoson/Yuque-MCP-Server
  • attio-mcp-server

    attio-mcp-server

    MCP server for enabling Attio CRM access via AI model context clients.

    attio-mcp-server implements a Model Context Protocol (MCP) server that facilitates communication between MCP clients, such as Claude, and the Attio CRM API. It enables reading and writing company notes and records within Attio by leveraging a bearer token for authentication. Designed for Node.js, it provides streamlined integration with Attio for applications utilizing AI-driven model context protocols.

    • ⭐ 16
    • MCP
    • hmk/attio-mcp-server
    • View all Alternatives

    Didn't find tool you were looking for?

    Be as detailed as possible for better results