Box MCP Server Integration

What does “Box” MCP Server do?

The Box MCP Server is a Python-based project that enables seamless integration between AI assistants and the Box API. Acting as a bridge, it allows AI-powered workflows to perform a range of tasks on Box, such as searching files, extracting text, running AI-powered queries, managing folders, and handling file uploads and downloads. Through the Model Context Protocol (MCP), the server standardizes how AI agents interact with Box data, making it easier for developers to automate document management, leverage AI for content analysis, and streamline collaboration. The Box MCP Server empowers teams to query, modify, and analyze files and folders at scale, enhancing productivity and unlocking new possibilities for AI-driven document workflows.

List of Prompts

No explicit prompt templates are documented in the repository.

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• box_who_am_i
  Get current user information and check connection status.

• box_authorize_app_tool
  Start the Box application authorization process.

• box_search_tool
  Search for files in Box using queries, file extensions, locations, and ancestor folder IDs.

• box_read_tool
  Read the text content of a Box file by ID.

• box_ask_ai_tool
  Ask Box AI about a file using a prompt.

• box_ask_ai_tool_multi_file
  Query Box AI with multiple files and a prompt.

• box_hubs_ask_ai_tool
  Ask Box AI about a hub using a hub ID and prompt.

• box_search_folder_by_name
  Locate a folder by its name.

• box_ai_extract_data
  Extract specified fields from a file using AI.

• box_list_folder_content_by_folder_id
  List the contents of a folder by folder ID, optionally recursively.

• box_manage_folder_tool
  Create, update, or delete folders in Box.

• box_upload_file_tool
  Upload files to Box.

Use Cases of this MCP Server

• Document Search and Retrieval
  Developers can automate searching for files or folders based on keywords, extensions, or content, making it easier to locate relevant documents within large Box repositories.

• AI-Assisted Content Analysis
  Use Box AI to extract structured data, summarize documents, or answer questions about file content, enabling intelligent document processing and insights.

• Folder and File Management
  Automate the creation, updating, and deletion of folders, as well as uploading and reading files, streamlining content organization and collaboration.

• Bulk Operations and Reporting
  List folder contents recursively and aggregate information for audit, reporting, or migration tasks.

• Integrating Box with AI Workflows
  Use Box as a context resource in AI-driven flows, allowing agents to access, analyze, and manipulate Box data as part of broader automated processes.

How to set it up

Windsurf

1. Ensure prerequisites (e.g., Node.js) are installed.

2. Locate your Windsurf configuration file.

3. Add the Box MCP Server using a JSON snippet in the mcpServers section:

   "mcpServers": {
     "box-mcp": {
       "command": "npx",
       "args": ["@box/mcp-server-box@latest"]
     }
   }
   

4. Save the configuration and restart Windsurf.

5. Verify setup by checking that the server responds to requests.

Securing API Keys

Use environment variables for sensitive credentials:

"mcpServers": {
  "box-mcp": {
    "command": "npx",
    "args": ["@box/mcp-server-box@latest"],
    "env": {
      "BOX_CLIENT_ID": "your-client-id",
      "BOX_CLIENT_SECRET": "your-client-secret"
    },
    "inputs": {}
  }
}

Claude

1. Install Node.js if required.

2. Open Claude’s configuration file.

3. Add the Box MCP Server in the mcpServers section:

   "mcpServers": {
     "box-mcp": {
       "command": "npx",
       "args": ["@box/mcp-server-box@latest"]
     }
   }
   

4. Save changes and restart Claude.

5. Confirm the MCP server is running.

Securing API Keys

"env": {
  "BOX_CLIENT_ID": "your-client-id",
  "BOX_CLIENT_SECRET": "your-client-secret"
}

Cursor

1. Install prerequisites as needed.

2. Edit your Cursor configuration file.

3. Insert the Box MCP server entry:

   "mcpServers": {
     "box-mcp": {
       "command": "npx",
       "args": ["@box/mcp-server-box@latest"]
     }
   }
   

4. Save and restart Cursor.

5. Verify integration.

Securing API Keys

"env": {
  "BOX_CLIENT_ID": "your-client-id",
  "BOX_CLIENT_SECRET": "your-client-secret"
}

Cline

1. Make sure Node.js and other prerequisites are installed.

2. Open the Cline configuration file.

3. Add Box MCP server configuration:

   "mcpServers": {
     "box-mcp": {
       "command": "npx",
       "args": ["@box/mcp-server-box@latest"]
     }
   }
   

4. Save and restart Cline.

5. Test the server connection.

Securing API Keys

"env": {
  "BOX_CLIENT_ID": "your-client-id",
  "BOX_CLIENT_SECRET": "your-client-secret"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "box-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “box-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support not documented

Based on the tables above, this MCP server is very strong in tool coverage and setup clarity but lacks documentation for prompt templates or explicit resource/roots/sampling support. Overall, it is a robust and practical integration for Box workflows but could benefit from richer MCP-specific features and documentation.

MCP Score