Box MCP Server
for AI Agents

Add a user to an enterprise group as a member or admin. Requires enterprise admin or co-admin permissions. Provide the user ID and group ID as nested objects. Returns 403 if the authenticated account lacks admin-level privileges for group membership management.

Adds files, folders, or web links to a specific hub, enabling content organization within collaborative workspaces. Essential for building and curating hub content by adding relevant materials to the collaborative space. This tool enables the population of hubs with relevant content, making it easy to organize materials within collaborative workspaces. You can add multiple items at once, supporting efficient hub content management and organization. **Key Features:** - Adds multiple items (files, folders, web links) to hubs in a single operation - Supports batch operations for efficient content organization - Works with all Box content types: files, folders, and web links - Provides confirmation of successful additions with detailed results **Supported Item Types:** - `file`: Box files of any type - `folder`: Box folders and their contents - `web_link`: External web links and bookmarks <examples> Add a single file to a hub: <input> { "hub_id": "12345", "items": [ {"id": "98765", "type": "file"} ] } </input> Add multiple items to a hub: <input> { "hub_id": "12345", "items": [ {"id": "98765", "type": "file"}, {"id": "54321", "type": "folder"}, {"id": "11111", "type": "web_link"} ] } </input> Add resources to a team hub: <input> { "hub_id": "55555", "items": [ {"id": "111111", "type": "folder"}, {"id": "222222", "type": "web_link"}, {"id": "333333", "type": "file"} ] } </input> </examples>

Creates a new Box Note in Box from markdown content. A Box Note is Box's native collaborative document format (.boxnote). The note name must be provided; the .boxnote extension is optional and will be appended if missing. **Key Features:** - Creates a native Box Note from markdown content - Use this tool instead of `upload_file` whenever the desired output is a Box Note **Important:** This tool only creates Box Notes. To create other text files (e.g. .txt, .md), use the `upload_file` tool instead.

Create a chunked upload session for large files

List all pending collaborations for a user

List all file and folder collaborations for a specific group, showing what content the group has access to and with what role. Requires enterprise admin or co-admin permissions — having manage_groups scope alone is not sufficient, the authenticated user must also have admin-level privileges in the Box Admin Console.

List all collaborations on a folder, showing which users and groups have access and their roles (editor, viewer, co-owner, etc.). Returns both pending and active collaborations. Use the collaboration_id from the response for update_collaboration or delete_collaboration operations.

List all collaborations on a file, showing which users and groups have access and their roles. Returns both pending and active collaborations. Use the collaboration_id from the response for update_collaboration or delete_collaboration operations.

List user and enterprise events

Retrieve information about a file

Retrieve a thumbnail of a file

Search Box for files, folders and web links by name or content.

List tasks on a file

Retrieve information about a file in trash

List items in a folder. Use folder_id "0" to list items in the root folder.

Retrieve information about a folder

Retrieve information about a folder in trash

List all items in trash

Get the current Box connection's unified credentials and identity.

List unified resource types in Box.

List unified resource users in Box.

Searches for folders by name within Box using keyword matching. This tool helps locate specific folders by their names and can be scoped to search within a particular parent folder. Returns basic folder information including ID, type, and name for each matching folder. The search performs a keyword-based match against folder names and can be limited to search within a specific ancestor folder. This is particularly useful for navigating complex folder structures, finding project folders, or locating organizational folders by name patterns. The tool uses Box's search API with folder type filtering, ensuring only folders (not files) are returned in results. Search results are limited to preserve performance and can be paginated using the limit parameter. **Date Range Filters:** Date range filters properties of the input schema: created_at_range, updated_at_range, deleted_at_range. Use comma-separated RFC3339 timestamps. **Format:** "start_date,end_date" where: - Omit start date to search all folders before end date: ",2023-12-31T23:59:59Z" - Omit end date to search from start date to the present: "2023-01-01T00:00:00Z," - Both dates for specific range: "2023-01-01T00:00:00Z,2023-12-31T23:59:59Z" <examples> Basic folder search: <input> { "folder_name": "Project Documents", "limit": 30 } </input> Search within specific parent folder: <input> { "folder_name": "2024 Reports", "ancestor_folder_id": "123456789", "limit": 50 } </input> Search for folders with partial name match: <input> { "folder_name": "Finance", "limit": 20 } </input> Limited results search: <input> { "folder_name": "Marketing Campaign", "ancestor_folder_id": "987654321", "limit": 10 } </input> Search in root directory and limit results by date: <input> { "folder_name": "Shared Resources", "created_at_range": "2023-01-01T00:00:00Z,2023-12-31T23:59:59Z" } </input> </examples>

Lists files, folders, and web links contained in a folder. Returns a paginated list of items with at least fields. Fields (id, type, name, etag) are always returned. Use folder_id "0" for the root folder. Supported fields include: id, type, name, etag, sequence_id, sha1, content_created_at, content_modified_at, created_at, created_by, modified_at, modified_by, owned_by, parent, path_collection, size, trashed_at, item_status, description, shared_link, classification, comment_count, disposition_at, expires_at, extension, has_collaborations, is_accessible_via_shared_link, is_associated_with_app_item, is_externally_owned, is_package, lock, metadata, permissions, representations, shared_link_permission_options, tags, uploader_display_name, version_number, watermark_info, file_version. <examples> Basic folder listing: <input> { "folder_id": "0", "limit": 50 } </input> List with specific fields: <input> { "folder_id": "123456789", "fields": ["id", "name", "type", "size", "modified_at", "created_by"], "limit": 100 } </input> Paginated listing: <input> { "folder_id": "987654321", "fields": ["id", "name", "type", "path_collection"], "limit": 30, "offset": 60 } </input> </examples>

Searches for files using keywords and supports metadata filters, file extension filtering (without dots), and field selection. Maps to Box's searchForContent API with comprehensive filtering capabilities. The response always includes core fields: id, name, description, type, and size. Each entry also includes `url` (Box web link for files and folders; web links use the API `url` when returned). The 'fields' parameter allows you to request additional fields beyond these core ones. All requested fields (core + additional) will be included in the API request and returned in the response. **Available Additional Fields:** fileVersion, sha1, contentCreatedAt, contentModifiedAt, createdAt, createdBy, modifiedAt, modifiedBy, ownedBy, parent, pathCollection, purgedAt, sharedLink, size, trashedAt, classification, commentCount, dispositionAt, expiresAt, extension, hasCollaborations, isAccessibleViaSharedLink, isAssociatedWithAppItem, isExternallyOwned, isPackage, lock, metadata, permissions, representations, sharedLinkPermissionOptions, tags, uploaderDisplayName, watermarkInfo **Date Range Filters:** Date range filters properties of the input schema: created_at_range, updated_at_range, deleted_at_range. Use comma-separated RFC3339 timestamps. **Format:** "start_date,end_date" where: - Omit start date to search all items before end date: ",2023-12-31T23:59:59Z" - Omit end date to search from start date to the present: "2023-01-01T00:00:00Z," - Both dates for specific range: "2023-01-01T00:00:00Z,2023-12-31T23:59:59Z" <examples> Basic keyword search (returns core fields only): <input> { "query": "contract agreement", "limit": 50 } </input> Advanced search with additional fields: <input> { "query": "quarterly report", "file_extensions": ["pdf", "docx"], "ancestor_folder_id": "123456789", "fields": ["createdAt", "modifiedAt", "size", "createdBy"] } </input> Searching by date: <input> { "query": "quarterly report", "file_extensions": ["pdf", "docx"], "ancestor_folder_id": "123456789", "created_at_range”: "2023-01-01T00:00:00Z,2023-12-31T23:59:59Z", "fields": ["createdAt"] } </input> Search with metadata filters and additional fields: <input> { "query": "invoice", "file_extensions": ["pdf"], "limit": 30, "fields": ["contentCreatedAt", "pathCollection", "metadata"], "mdfilters": [ { "scope": "enterprise", "templateKey": "invoiceTemplate", "filters": { "amount": { "gt": 1000, "lt": 5000 }, "status": "approved", "department": "finance" } } ] } </input> Multi-template metadata search with custom fields: <input> { "query": "project document", "fields": ["modifiedBy", "sharedLink", "tags", "permissions"], "mdfilters": [ { "scope": "enterprise", "templateKey": "projectTemplate", "filters": { "priority": "high", "deadline": { "gt": "2024-01-01" } } }, { "scope": "global", "templateKey": "reviewTemplate", "filters": { "reviewer": "[email protected]" } } ] } </input> </examples>

Get the text content of a file from Box. Prefers the markdown representation (preserves document structure for better LLM use) and falls back to extracted text when markdown is not available. If neither representation is available or both are still pending, an error is returned. Using this tool is preferred over the ai_qa_single_file tool since it is faster and more efficient. Works for files with text representations such as PDFs, documents, spreadsheets, presentations, code, etc. Optional version_id reads a past version (GET /files/{file_id}/versions/{version_id}); omit it for the current version. Use list_file_versions to get version_id values. **Key Features:** - Markdown representation preferred (structure preserved for LLMs); fallback to extracted text - Optional version_id for a past file version - 50MB file size limit enforcement - Clear error messages for unsupported operations <examples> Extract text content from a file: { "file_id": "123456789", } Extract text content from a past file version: { "file_id": "123456789", "version_id": "987654321", } <output> { "content": [ { "type": "text", "text": "This is the extracted text content from the file..." } ] } </output> </examples>

Gets comprehensive file information from Box. Returns essential fields by default (id, name, extension, createdBy, modifiedBy, createdAt, modifiedAt). Use 'fields' parameter to request additional properties. **Common useful fields:** size, description, tags, metadata, permissions, shared_link, parent, path_collection, file_version, sha1, lock, classification, comment_count, has_collaborations, representations, watermark_info, uploader_display_name, content_created_at, content_modified_at, item_status, expires_at, trashed_at. <examples> Basic file info: <input>{"file_id": "123456789"}</input> File with metadata and permissions: <input> { "file_id": "987654321", "fields": ["id", "name", "size", "permissions", "tags", "metadata", "shared_link"] } </input> Detailed file analysis: <input> { "file_id": "555666777", "fields": ["id", "name", "description", "file_version", "sha1", "path_collection", "classification", "comment_count", "has_collaborations"] } </input> </examples>

Retrieves comprehensive information about a folder in Box. Returns essential fields by default (id, name, createdBy, modifiedBy, createdAt, modifiedAt). Use 'fields' parameter to request additional properties. **Common useful fields:** size, description, tags, metadata, permissions, shared_link, parent, path_collection, folder_upload_email, has_collaborations, allowed_invitee_roles, can_non_owners_invite, can_non_owners_view_collaborators, is_collaboration_restricted_to_enterprise, classification, allowed_shared_link_access_levels, content_created_at, content_modified_at, item_status, sync_state, watermark_info, trashed_at. **Note:** Only request 'item_collection' when the user explicitly asks for folder contents. Use 'list_folder_content_by_folder_id' for browsing folder items instead. <examples> Basic folder info: <input>{"folder_id": "123456789"}</input> Folder with permissions and collaboration settings: <input> { "folder_id": "987654321", "fields": ["id", "name", "size", "permissions", "can_non_owners_invite", "has_collaborations"] } </input> Detailed folder analysis with settings: <input> { "folder_id": "555666777", "fields": ["id", "name", "description", "path_collection", "folder_upload_email", "allowed_invitee_roles", "classification", "shared_link", "tags"] } </input> </examples>

Lists all collaborations for multiple files and folders in a single request. This tool efficiently aggregates collaboration information across different item types, making multiple API calls as needed and providing comprehensive results with error handling for items that cannot be accessed. The tool processes up to 10 items simultaneously, handling both files and folders. It returns detailed collaboration information including user details, roles, status, and timestamps. Partial failures are handled gracefully - if some items fail to load, the tool still returns collaborations for successful items along with error details for failed requests. <examples> Basic file collaboration listing: <input> { "items": [ { "id": "123456789", "type": "file" } ] } </input> Single folder collaboration listing: <input> { "items": [ { "id": "987654321", "type": "folder" } ] } </input> Multiple items for bulk analysis: <input> { "items": [ { "id": "111222333", "type": "file" }, { "id": "444555666", "type": "file" }, { "id": "777888999", "type": "folder" }, { "id": "101112131", "type": "folder" } ] } </input> </examples>

Returns the schema for a metadata template. Shield template "securityClassification-6VMVochwUWo": option colorID is normalized from staticConfig (default Yellow=0). Palette: 0=Yellow, 1=Orange, 2=Red, 3=Purple, 4=LightBlue, 5=DarkBlue, 6=Green, 7=Grey.

Searches for files using SQL-like metadata queries. Requires: from (e.g. enterprise_123456.templateKey from list_metadata_templates), fields (field keys from get_metadata_template_schema). ancestor_folder_id defaults to "0" (root) if omitted. Use list_metadata_templates and get_metadata_template_schema first to discover templates and field keys.

Retrieves comprehensive information about a specific hub including metadata, creation details, and administrative information. Provides complete hub context for understanding ownership, timing, and purpose. This tool is essential for understanding hub context, ownership, and management information. It provides the complete picture of a hub's properties, helping users understand when it was created, by whom, and its current status. **Key Features:** - Retrieves detailed hub information including title, description, and metadata - Provides creation and modification timestamps - Shows hub ownership and creator information - Returns complete hub context for administrative and management purposes <examples> Get detailed information about a specific hub: <input> { "hub_id": "12345" } </input> </examples>

Retrieves all items within a specific hub including files, folders, and web links. Essential for exploring the contents of collaborative workspaces and understanding what resources are available in a hub. This tool provides comprehensive access to hub contents with pagination support, allowing you to browse through all materials that have been added to a collaborative workspace. Perfect for content discovery and hub content management. **Key Features:** - Retrieves all items (files, folders, web links) within a specific hub - Supports pagination for hubs with large amounts of content - Returns detailed item information including names, types, and IDs - Configurable result limits for efficient data retrieval <examples> Get items in a specific hub: <input> { "hub_id": "12345" } </input> Get hub items with pagination: <input> { "hub_id": "67890", "limit": 50, "marker": "next_marker_value" } </input> Get first 25 items from a hub: <input> { "hub_id": "11111", "limit": 25 } </input> </examples>

Displays an interactive preview widget for a Box file directly in chat. Supports: ai, bmp, cr2, crw, csv, dng, doc, docx, dwg, eml, eps, gdoc, gif, gsheet, gslide, gslides, heic, htm, html, idml, indd, indt, inx, jpeg, jpg, key, nef, numbers, odp, ods, odt, pages, pdf, png, ppt, pptx, ps, psd, raf, raw, rtf, svg, svs, tga, tif, tiff, tsv, webp, wpd, xhtml, xls, xlsm, xlsx. PDF uses direct download; other types use the appropriate representation (e.g. PDF for documents, JPG/PNG for images). Use when user wants to view file contents without downloading. For file metadata, use get_file_info instead. If the preview payload would exceed 3MB (full file for PDFs; generated representation for other types), do not use this. Do not attempt to generate an interactive artifact. When a preview is open, the widget sends file preview context (fileId, fileName, currentPage) into the conversation. If the user asks about "this graph", "explain this", "what's on this page", or similar, look for that context and call get_preview_page(fileId, currentPage) to fetch the page image—do not ask the user which page they are on.

Use when user asks follow-up question to a file previewed with get_file_preview ("Explain this...", "What does ____ mean?")Returns the current preview page as an image so you can analyze it (figures, text, charts, etc.). You cannot see the page content until you call this tool. Required workflow: 1. Find the file preview context in the conversation. The preview widget sends it as content like: "Current file preview: fileId=123, fileName=doc.pdf, currentPage=3. Use get_preview_page with this fileId and currentPage...". Look for this before calling. 2. Extract fileId and currentPage from that context. If the user asks about "this page", "these figures", "what's on the page", use currentPage from the context. If they name a page (e.g. "page 7"), use that number instead. 3. Call get_preview_page(fileId, currentPage) to fetch the page image. You must call this tool to see the page—there is no other way to view its content. 4. Use the returned image to answer the user's question. Do not call with a fileId or page from elsewhere. If no file preview context is present (no "Current file preview: fileId=..." in the conversation), do not call. Supported extensions: ai, bmp, cr2, crw, csv, dng, doc, docx, dwg, eml, eps, gdoc, gif, gsheet, gslide, gslides, heic, htm, html, idml, indd, indt, inx, jpeg, jpg, key, nef, numbers, odp, ods, odt, pages, pdf, png, ppt, pptx, ps, psd, raf, raw, rtf, svg, svs, tga, tif, tiff, tsv, webp, wpd, xhtml, xls, xlsm, xlsx.

Search for files and folders that have specific metadata values applied. This is a read-only search/query tool — it does NOT create, update, or delete metadata. Use create_file_metadata, update_file_metadata, or delete_file_metadata for write operations. Uses SQL-like syntax to filter by metadata field values.

Retrieve the profile of the currently authenticated user, including their user ID, name, email, avatar URL, and enterprise info. Does not require admin permissions — any authenticated user can call this. Use this to get the current user's ID when you need it for other operations.

List all enterprise users with their IDs, names, and email addresses. Requires enterprise admin or co-admin permissions with manage_managed_users scope. Use filter_term to search by name or email prefix. Use user_type to filter by managed, external, or all users. If you already have a user's email address (e.g. for task assignment), you can pass it directly to assign_task via assign_to.login instead of looking up their user ID here.

Remove a user from a group

Remove the lock from a file so other users can move, rename or change it again.

Promote a previous file version to be the current version

Restore a previously deleted file version from the file's version history. This does NOT restore files from the trash — use restore_file for that. Requires the file_id and the file_version_id of the deleted version (obtainable from list_file_versions). Only works on premium Box accounts that support version tracking.

Restore a file from trash

Permanently delete a trashed file

Restore a folder from trash

Permanently delete a trashed folder

Returns detailed information about the currently authenticated Box user. This tool provides comprehensive user profile data including basic identification, contact information, role details, and account settings. No input parameters are required as it retrieves information for the authenticated user making the request. This tool is essential for understanding the current user context, verifying authentication status, and obtaining user-specific information for personalization or access control purposes. It's particularly useful when building user-aware applications or when you need to identify the current user's permissions and organizational role. The response includes core user attributes such as ID, name, email, login, role, job title, and additional account details like space usage, language preferences, and timezone settings. <examples> Get current user information: <input> {} </input> </examples>

Assign a task to a user by user ID or email address. The user receives a notification. You can use either assign_to.id (user ID) or assign_to.login (email address) — you do not need to look up the user ID first if you already have their email.