Box MCP Server (Remote)

Box MCP Server (Remote)

Securely connect AI agents to Box content and Box AI using the Model Context Protocol.

View on GitHub
0
Stars
3
Forks
0
Watchers
0
Issues
Box MCP Server (Remote) enables AI agent platforms to securely interact with Box data and AI-powered tools via the Model Context Protocol. It supports OAuth-based authentication and provides various capabilities, including user identification, file and folder operations, and access to Box AI tools. The service exposes an endpoint for easy integration by MCP-compatible clients while ensuring data never leaves the Box environment. It offers both admin console and developer console setup options and comprehensive documentation for connection.

Key Features

MCP-compatible remote server endpoint
OAuth 2.0 authentication and authorization
User identification and info retrieval
Read and search file and folder content
Metadata extraction from files
Q&A capabilities across files
Integration with Box AI tools
No data export—keeps content within Box
Admin Console and Developer Console support for setup
Resource and authorization server metadata exposure

Use Cases

Connecting AI copilots to corporate Box accounts for document processing
Enabling secure access for AI agents to perform searches and retrieve files in Box
Running Q&A and knowledge extraction on Box content using Box AI
Providing OAuth-protected gateways for third-party AI platforms
Integrating Box file and folder operations with model context workflows
Building AI-driven workflow automations for enterprise content
Granting granular content permissions to AI agents within enterprise environments
Enabling contextual document retrieval for assistants like Claude or Copilot
Supporting federated AI agent architectures without exporting enterprise data
Administering secure data access and AI tooling via Box's Admin Console for large organizations

README

Box MCP Server (Remote)

Securely connect MCP-compatible agents to your Box content and Box AI—without moving data out of Box.

Endpoint: https://mcp.box.com

Overview

The remote Box MCP server lets AI agent platforms (e.g., Copilot Studio, Claude, Mistral Le Chat) connect to Box to securely query and use Box data and AI-powered tools, while keeping content protected. Authorization is handled via OAuth so users can grant controlled access from within the client they’re using.

Learn more in the remote Box MCP server guide

Looking for the self-hosted/local version? See box-community/mcp-server-box.

Capabilities

The remote Box MCP server provides tools across several areas, such as:

  • User info (e.g., identify the authenticated user)
  • File and folder operations (read content, list folders, search files/folders, etc.)
  • Box AI tools (Q&A across files, metadata extraction, etc.)

For the complete and most up-to-date set of supported tools, see the remote Box MCP server documentation.

Setup

To connect an MCP client to the remote Box MCP server, you’ll first configure an OAuth app in Box, then use its credentials in your client. The preferred path is to use the predefined Box MCP Server integration in the Admin Console, but in certain flows (e.g., the GitHub MCP registry), you may need to create your own OAuth app in the Developer Console instead.

1. Configure an OAuth app in Box

Choose one of the following options:

  • Admin Console flow (preferred): Enable or configure the Box MCP server from Admin Console → Integrations.
  • Developer Console flow: Create an OAuth app with the proper redirect URI and scopes.

For detailed instructions, see the remote Box MCP server guide.

2. Connect from your MCP client

Most clients or platforms let you add a remote MCP server by URL and will guide you through the OAuth flow. Here are some of the details you’ll typically need to provide:

  • Endpoint URL: https://mcp.box.com
  • Name: a name of your choice (e.g., box-remote-mcp)
  • Authorization: Bearer token (via OAuth 2.0)
  • Client ID and Client Secret: obtained from your app’s credentials (Admin Console for the predefined Box MCP Server integration, or Developer Console if you created your own OAuth app)
  • Redirect URI: provided by your client and must be added to your app configuration (via the Admin Console or Developer Console, depending on your flow)

See the remote Box MCP server guide for client-specific connection examples (Claude, Copilot Studio, Le Chat).

OAuth & Discovery

The remote Box MCP server is an OAuth‑protected resource backed by Box’s authorization server:

For implementation details, see the Box authentication guide.

Using tokens with the Box API

All Box API calls require a valid Access Token. Example:

bash
curl https://api.box.com/2.0/users/me \
  -H "authorization: Bearer <ACCESS_TOKEN>"

Terms

Use of the Box MCP server and Box APIs is subject to the Box Terms of Service:
https://www.box.com/legal/termsofservice

Support & Docs

Star History

Star History Chart

Repository Owner

box
box

Organization

Repository Details

Default Branch main
Size 3 KB
Contributors 1
License MIT License
MCP Verified Nov 12, 2025

Tags

OAuth file management Remote Server

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

  • box-mcp-server

    box-mcp-server

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

    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.

    • ⭐ 10
    • MCP
    • hmk/box-mcp-server
  • 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
  • QuantConnect MCP Server

    QuantConnect MCP Server

    Official bridge for secure AI access to QuantConnect's algorithmic trading cloud platform

    QuantConnect MCP Server enables artificial intelligence systems such as Claude and OpenAI to interface with QuantConnect's cloud platform through an official, secure, and dockerized implementation of the Model Context Protocol (MCP). It facilitates automated project management, strategy writing, backtesting, and live deployment by exposing a comprehensive suite of API tools for users with valid access credentials. As the maintained official version, it ensures security, easy deployment, and cross-platform compatibility for advanced algorithmic trading automation.

    • ⭐ 50
    • MCP
    • QuantConnect/mcp-server
  • MCP Server for Odoo

    MCP Server for Odoo

    Connect AI assistants to Odoo ERP systems using the Model Context Protocol.

    MCP Server for Odoo enables AI assistants such as Claude to interact seamlessly with Odoo ERP systems via the Model Context Protocol (MCP). It provides endpoints for searching, creating, updating, and deleting Odoo records using natural language while respecting access controls and security. The server supports integration with any Odoo instance, includes smart features like pagination and LLM-optimized output, and offers both demo and production-ready modes.

    • ⭐ 101
    • MCP
    • ivnvxd/mcp-server-odoo
  • Teamwork MCP Server

    Teamwork MCP Server

    Seamless Teamwork.com integration for Large Language Models via the Model Context Protocol

    Teamwork MCP Server is an implementation of the Model Context Protocol (MCP) that enables Large Language Models to interact securely and programmatically with Teamwork.com. It offers standardized interfaces, including HTTP and STDIO, allowing AI agents to perform various project management operations. The server supports multiple authentication methods, an extensible toolset architecture, and is designed for production deployments. It provides read-only capability for safe integrations and robust observability features.

    • ⭐ 11
    • MCP
    • Teamwork/mcp
  • Authenticator App MCP Server

    Authenticator App MCP Server

    Secure MCP server for AI-assisted access to 2FA codes and passwords.

    Authenticator App MCP Server provides a secure Model Context Protocol (MCP) server enabling AI agents to interact with authentication credentials, such as 2FA codes and passwords. It facilitates automated login processes for AI assistants while maintaining robust security by requiring access tokens and integrating with the Authenticator App desktop client. This solution streamlines the management of user credentials across multiple platforms and websites, ensuring seamless and secure credential retrieval by AI agents.

    • ⭐ 27
    • MCP
    • firstorderai/authenticator_mcp
    • View all Alternatives

    Didn't find tool you were looking for?

    Be as detailed as possible for better results