Box

93 tools. 50 can modify or destroy data without limits.

9 destructive tools with no built-in limits. Policy required.

Last updated:

50 can modify or destroy data
43 read-only
93 tools total
Read (43) Write / Execute (41) Destructive / Financial (9)

Destructive tools (box_collaboration_delete_tool, box_docgen_template_delete_tool, box_file_delete_tool) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (box_collaboration_file_group_by_group_id_tool, box_collaboration_file_user_by_user_id_tool, box_collaboration_file_user_by_user_login_tool) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (box_authorize_app_tool) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Box. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @box-community/mcp-server-box
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
box_collaboration_delete_tool:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
box_collaboration_file_group_by_group_id_tool:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
box_ai_ask_file_multi_tool:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

WRITE 40 tools
Write box_collaboration_file_group_by_group_id_tool Write box_collaboration_file_user_by_user_id_tool Write box_collaboration_file_user_by_user_login_tool Write box_collaboration_folder_group_by_group_id_tool Write box_collaboration_folder_user_by_user_id_tool Write box_collaboration_update_tool Write box_docgen_create_batch_tool Write box_docgen_create_single_file_from_user_input_tool Write box_docgen_template_create_tool Write box_file_copy_tool Write box_file_lock_tool Write box_file_move_tool Write box_file_rename_tool Write box_file_retention_date_clear_tool Write box_file_retention_date_set_tool Write box_file_set_description_tool Write box_file_unlock_tool Write box_folder_copy_tool Write box_folder_create_tool Write box_folder_favorites_add_tool Write box_folder_favorites_remove_tool Write box_folder_move_tool Write box_folder_rename_tool Write box_folder_set_collaboration_tool Write box_folder_set_description_tool Write box_folder_tag_add_tool Write box_folder_tag_remove_tool Write box_metadata_set_instance_on_file_tool Write box_metadata_template_create_tool Write box_metadata_update_instance_on_file_tool Write box_shared_link_file_create_or_update_tool Write box_shared_link_folder_create_or_update_tool Write box_shared_link_web_link_create_or_update_tool Write box_task_assign_by_email_tool Write box_task_assign_by_user_id_tool Write box_task_complete_create_tool Write box_task_review_create_tool Write box_task_update_tool Write box_web_link_create_tool Write box_web_link_update_by_id_tool
READ 43 tools
Read box_ai_ask_file_multi_tool Read box_ai_ask_file_single_tool Read box_ai_ask_hub_tool Read box_ai_extract_freeform_tool Read box_ai_extract_structured_enhanced_using_fields_tool Read box_ai_extract_structured_using_fields_tool Read box_ai_extract_structured_using_template_tool Read box_collaboration_list_by_file_tool Read box_collaboration_list_by_folder_tool Read box_docgen_get_job_by_id_tool Read box_docgen_list_jobs_by_batch_tool Read box_docgen_template_get_by_id_tool Read box_docgen_template_get_by_name_tool Read box_docgen_template_list_jobs_tool Read box_docgen_template_list_tags_tool Read box_docgen_template_list_tool Read box_file_info_tool Read box_folder_info_tool Read box_folder_items_list_tool Read box_folder_list_tags_tool Read box_groups_list_by_user_tool Read box_groups_list_members_tool Read box_groups_search_tool Read box_metadata_get_instance_on_file_tool Read box_metadata_template_get_by_key_tool Read box_metadata_template_get_by_name_tool Read box_metadata_template_list_tool Read box_search_folder_by_name_tool Read box_search_tool Read box_shared_link_file_find_by_shared_link_url_tool Read box_shared_link_file_get_tool Read box_shared_link_folder_find_by_shared_link_url_tool Read box_shared_link_folder_get_tool Read box_task_assignment_details_tool Read box_task_assignments_list_tool Read box_task_details_tool Read box_task_file_list_tool Read box_users_list_tool Read box_users_locate_by_email_tool Read box_users_locate_by_name_tool Read box_users_search_by_name_or_email_tool Read box_web_link_get_by_id_tool Read box_who_am_i
Can an AI agent delete data through the Box MCP server? +

Yes. The Box server exposes 9 destructive tools including box_collaboration_delete_tool, box_docgen_template_delete_tool, box_file_delete_tool. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Box? +

The Box server has 40 write tools including box_collaboration_file_group_by_group_id_tool, box_collaboration_file_user_by_user_id_tool, box_collaboration_file_user_by_user_login_tool. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Box MCP server expose? +

93 tools across 4 categories: Destructive, Execute, Read, Write. 43 are read-only. 50 can modify, create, or delete data.

How do I add Intercept to my Box setup? +

One line change. Instead of running the Box server directly, prefix it with Intercept: intercept -c box.yaml -- npx -y @@box-community/mcp-server-box. Download a pre-built policy from policylayer.com/policies/box and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.