Box MCP logo

Integrate Box MCP with your AI CRM

Search, retrieve, analyze, and manage enterprise content stored in Box through Box's hosted MCP server.

Explore Triggers and Actions

Add items to hub

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>

ActionTry it

Ai extract freeform

Extracts metadata from files using Box AI in freeform format without requiring predefined template structures. This tool leverages Box AI to extract any type of information from documents using natural language instructions, allowing for flexible and unstructured metadata extraction. Unlike structured extraction tools that require predefined templates, this tool allows you to specify custom prompts to extract specific information from documents. You can extract dates, names, financial figures, key terms, or any other data by describing what you want in natural language. The tool processes files with text representations up to 1MB in size and supports various file types including documents, PDFs, presentations, and text files. You can analyze single files or multiple files simultaneously for comparative analysis. <examples> Basic document information extraction: <input> { "file_ids": ["123456789"], "prompt": "Extract the customer name, invoice number, and total amount from this document." } </input> Contract analysis: <input> { "file_ids": ["987654321"], "prompt": "Extract all dates, names, and key financial figures mentioned in this contract. Format as a structured list." } </input> Multi-file analysis: <input> { "file_ids": ["111222333", "444555666"], "prompt": "Compare these two proposals and extract the key differences in pricing, timeline, and deliverables." } </input> Custom field extraction: <input> { "file_ids": ["777888999"], "prompt": "Extract the following information if available: company name, contact email, project deadline, budget range, and main objectives." } </input> Structured output request: <input> { "file_ids": ["555666777"], "prompt": "Extract all financial data and format as JSON with keys: amount, currency, date, description." } </input> Missing data handling: <input> { "file_ids": ["888999000"], "prompt": "Extract client name, project start date, and budget. If any field is not found, return 'Not specified'." } </input> </examples>

ActionTry it

Ai extract structured from fields

Extracts structured metadata from files using Box AI based on custom field definitions. This tool leverages Box AI to process documents and return extracted data as structured key-value pairs, supporting various field types including strings, dates, numbers, enums, and multi-select options. This tool provides structured output by defining custom fields that specify what information to extract and how to structure it. The tool processes files with text representations and supports various file types including documents, PDFs, presentations, and text files. <examples> Custom fields extraction: <input> { "file_ids": ["123456789"], "fields": [ { "key": "customer_name", "displayName": "Customer Name", "description": "The name of the customer", "type": "string", "prompt": "Extract the customer name from the document" }, { "key": "invoice_amount", "displayName": "Invoice Amount", "description": "Total invoice amount", "type": "float" }, { "key": "payment_status", "displayName": "Payment Status", "description": "Current payment status", "type": "enum", "options": [ {"key": "paid"}, {"key": "pending"}, {"key": "overdue"} ] } ] } </input> Multi-file structured extraction with fields: <input> { "file_ids": ["111222333", "444555666"], "fields": [ { "key": "document_type", "displayName": "Document Type", "type": "enum", "options": [ {"key": "contract"}, {"key": "invoice"}, {"key": "proposal"} ] }, { "key": "key_dates", "displayName": "Important Dates", "type": "multiSelect", "options": [ {"key": "start_date"}, {"key": "end_date"}, {"key": "due_date"} ] } ] } </input> Complex field extraction: <input> { "file_ids": ["777888999"], "fields": [ { "key": "company_info", "displayName": "Company Information", "description": "Company name and contact details", "type": "string", "prompt": "Extract company name, address, and main contact information" }, { "key": "contract_value", "displayName": "Contract Value", "description": "Total contract amount in USD", "type": "float", "prompt": "Find the total contract value, convert to USD if needed" }, { "key": "signature_date", "displayName": "Signature Date", "description": "Date when contract was signed", "type": "date" } ] } </input> </examples>

ActionTry it

Ai extract structured from fields enhanced

Extracts structured metadata from files using Box AI's Enhanced Extract Agent based on custom field definitions. This tool leverages Box AI to process documents and return extracted data as structured key-value pairs, supporting various field types including strings, dates, numbers, enums, and multi-select options. It uses a specialized AI agent (enhanced_extract_agent) that provides improved extraction capabilities compared to the standard extraction. **IMPORTANT: This tool should ONLY be used when the user explicitly requests the "enhanced extract agent" or specifically asks for enhanced extraction capabilities. It is more expensive than the standard aiExtractStructuredFromFields tool and should not be used as a default option.** This tool provides structured output by defining custom fields that specify what information to extract and how to structure it. The tool processes files with text representations and supports various file types including documents, PDFs, presentations, and text files. You can analyze single files or multiple files simultaneously. <examples> Enhanced custom fields extraction: <input> { "file_ids": ["123456789"], "fields": [ { "key": "customer_name", "displayName": "Customer Name", "description": "The name of the customer", "type": "string", "prompt": "Extract the customer name from the document" }, { "key": "invoice_amount", "displayName": "Invoice Amount", "description": "Total invoice amount", "type": "float" }, { "key": "payment_status", "displayName": "Payment Status", "description": "Current payment status", "type": "enum", "options": [ {"key": "paid"}, {"key": "pending"}, {"key": "overdue"} ] } ] } </input> Enhanced multi-file structured extraction with fields: <input> { "file_ids": ["111222333", "444555666"], "fields": [ { "key": "document_type", "displayName": "Document Type", "type": "enum", "options": [ {"key": "contract"}, {"key": "invoice"}, {"key": "proposal"} ] }, { "key": "key_dates", "displayName": "Important Dates", "type": "multiSelect", "options": [ {"key": "start_date"}, {"key": "end_date"}, {"key": "due_date"} ] } ] } </input> Enhanced complex field extraction: <input> { "file_ids": ["777888999"], "fields": [ { "key": "company_info", "displayName": "Company Information", "description": "Company name and contact details", "type": "string", "prompt": "Extract company name, address, and main contact information" }, { "key": "contract_value", "displayName": "Contract Value", "description": "Total contract amount in USD", "type": "float", "prompt": "Find the total contract value, convert to USD if needed" }, { "key": "signature_date", "displayName": "Signature Date", "description": "Date when contract was signed", "type": "date" } ] } </input> </examples>

ActionTry it

Ai extract structured from metadata template

Extracts structured metadata from files using Box AI based on an existing metadata template. This tool leverages Box AI to process documents and return extracted data following the structure defined in a Box metadata template. This tool uses metadata templates that have been previously created in Box, allowing you to consistently extract information based on predefined schemas. The tool processes files with text representations and supports various file types including documents, PDFs, presentations, and text files. <examples> Metadata template extraction: <input> { "file_ids": ["987654321"], "template_key": "invoiceTemplate", "scope": "enterprise_12345" } </input> Multi-file extraction with template: <input> { "file_ids": ["111222333", "444555666"], "template_key": "contractTemplate", "scope": "enterprise_12345" } </input> Global template extraction: <input> { "file_ids": ["777888999"], "template_key": "properties", "scope": "global" } </input> </examples>

ActionTry it

Ai extract structured from metadata template enhanced

Extracts structured metadata from files using Box AI's Enhanced Extract Agent based on an existing metadata template. This tool leverages Box AI to process documents and return extracted data following the structure defined in a Box metadata template. It uses a specialized AI agent (enhanced_extract_agent) that provides improved extraction capabilities compared to the standard extraction. **IMPORTANT: This tool should ONLY be used when the user explicitly requests the "enhanced extract agent" or specifically asks for enhanced extraction capabilities. It is more expensive than the standard aiExtractStructuredFromMetadataTemplate tool and should not be used as a default option.** The tool processes files with text representations and supports various file types including documents, PDFs, presentations, and text files. You can analyze single files or multiple files simultaneously. <examples> Metadata template extraction: <input> { "file_ids": ["987654321"], "template_key": "invoiceTemplate", "scope": "enterprise_12345" } </input> Multi-file extraction with template: <input> { "file_ids": ["111222333", "444555666"], "template_key": "contractTemplate", "scope": "enterprise_12345" } </input> Global template extraction: <input> { "file_ids": ["777888999"], "template_key": "properties", "scope": "global" } </input> </examples>

ActionTry it

Ai qa hub

Ask a question to a Box Hub using Box AI. This tool leverages Box AI to analyze hub content and provide intelligent responses to questions about the hub's resources, documents, and related materials. Hubs are collaborative spaces in Box that contain multiple files, folders, and resources organized around specific topics or projects. Box AI analyzes the content within the hub to provide comprehensive answers based on all accessible materials. This is particularly useful for getting insights across multiple documents and resources within a hub context, making it ideal for project-wide questions, content summaries, and cross-document analysis. **Citations:** The response includes citations as a separate content item that indicate which sources were referenced when generating the answer, allowing you to verify the AI's reasoning and locate relevant content. Citations are only returned when available and each citation includes the referenced content snippet, source file ID, and file name. <examples> General hub inquiry: <input> { "hub_id": "123456789", "question": "What is the main purpose and scope of this project hub?" } </input> Content analysis across hub: <input> { "hub_id": "987654321", "question": "What are the key milestones and deliverables mentioned across the documents in this hub?" } </input> Resource overview: <input> { "hub_id": "555666777", "question": "Summarize the current status and progress based on all available documents." } </input> Cross-document insights: <input> { "hub_id": "111222333", "question": "What are the main challenges and solutions discussed across the project materials?" } </input> Hub content summary: <input> { "hub_id": "444555666", "question": "Provide an overview of all the key information available in this hub." } </input> Collaborative analysis: <input> { "hub_id": "777888999", "question": "Based on all the documents in this hub, what recommendations can you make for next steps?" } </input> </examples>

ActionTry it

Ai qa multi file

Ask a question to multiple files using Box AI. This tool leverages Box AI to analyze content across multiple files simultaneously and provide intelligent responses that can compare, contrast, and synthesize information from all provided files. This is particularly useful for cross-document analysis, finding common themes, identifying differences, and getting comprehensive insights across related documents. Box AI processes all files together using the multi_item_qa mode, allowing for sophisticated analysis that spans multiple documents. This enables comparative analysis, pattern recognition across documents, and comprehensive answers that draw from the collective content of all specified files. **Citations:** The response includes citations as a separate content item that indicate which sources were referenced when generating the answer, allowing you to verify the AI's reasoning and locate relevant content. Citations are only returned when available and each citation includes the referenced content snippet, source file ID, and file name. <examples> Basic multi-file question: <input> { "file_ids": ["123456789", "987654321"], "question": "What are the common themes across these documents?" } </input> Comparative analysis: <input> { "file_ids": ["111222333", "444555666", "777888999"], "question": "Compare the methodologies discussed in these research papers." } </input> Cross-document data extraction: <input> { "file_ids": ["555666777", "888999000"], "question": "List all the key dates and milestones mentioned across these project documents." } </input> Comprehensive analysis: <input> { "file_ids": ["123456789", "987654321", "111222333"], "question": "Based on all these financial reports, what trends and recommendations can you identify?" } </input> Finding differences: <input> { "file_ids": ["444555666", "777888999"], "question": "What are the main differences in approach between these two proposals?" } </input> Synthesis and summary: <input> { "file_ids": ["123456789", "987654321", "111222333", "444555666"], "question": "Provide a comprehensive summary that synthesizes the key insights from all these documents." } </input> Pattern identification: <input> { "file_ids": ["555666777", "888999000", "123456789"], "question": "What patterns or recurring issues can you identify across these incident reports?" } </input> </examples>

ActionTry it

Ai qa single file

Ask a question to a single file using Box AI. This tool leverages Box AI to analyze file content and provide intelligent responses to questions about the file. Supports various file types including documents, PDFs, presentations, and text files. The AI analyzes the file content and returns an answer based on the question asked. Box AI handles text documents with text representations up to 1MB in size. If the text file size exceeds 1MB, the first 1MB of text representation will be processed. **Citations:** The response includes citations as a separate content item that indicate which sources were referenced when generating the answer, allowing you to verify the AI's reasoning and locate relevant content. Citations are only returned when available and each citation includes the referenced content snippet, source file ID, and file name. <examples> Basic file question: <input> { "file_id": "123456789", "question": "What is the main topic of this document?" } </input> Specific content inquiry: <input> { "file_id": "987654321", "question": "What are the key findings mentioned in the executive summary?" } </input> Data extraction: <input> { "file_id": "555666777", "question": "List all the dates mentioned in this contract." } </input> Analysis request: <input> { "file_id": "111222333", "question": "What are the pros and cons discussed in this report?" } </input> Complex question: <input> { "file_id": "444555666", "question": "Based on the financial data in this spreadsheet, what trends can you identify?" } </input> </examples>

ActionTry it

Copy file

Copies an existing file to a destination folder in Box (see Box API Copy file). The source file is not modified. Provide `parent_folder_id` as the folder that will contain the new copy; use `"0"` for the user's root folder. Optionally set `name` to rename the copy; otherwise the original file name is used. **Key features:** - Destination folder external-access guard (same as other write tools) - Optional new name for the copied file <examples> Copy a file into a folder: { "file_id": "123456789", "parent_folder_id": "987654321" } Copy a file to the user's root folder with a new name: { "file_id": "123456789", "parent_folder_id": "0", "name": "Quarterly-report-copy.docx" } </examples>

ActionTry it

Copy folder

Copies an existing folder to a destination parent folder in Box (see Box API Copy folder). The source folder is not modified. Provide `parent_folder_id` as the folder that will contain the new copy; use `"0"` for the user's root folder. The root folder (`folder_id` `"0"`) cannot be copied. Optionally set `name` for the new copy; otherwise the original folder name is used. **Key features:** - Destination folder external-access guard (same as other write tools) - Optional new name for the copied folder <examples> Copy a folder into another folder: { "folder_id": "123456789", "parent_folder_id": "987654321" } Copy a folder to the user's root with a new name: { "folder_id": "123456789", "parent_folder_id": "0", "name": "Project-backup" } </examples>

ActionTry it

Copy hub

Creates a copy of an existing Box Hub via the Hubs v3 API (`POST /v3/hubs/{id}:copy`). The source hub is not modified. Copies the source hub's description (unless overridden) and shareable items into the new hub by setting `includeItems` to `true`. **Important:** Only items the user has permission to share into the new hub are copied. Items the user can view only through the hub itself (without share permission) are not copied. **hub_id** (required): The source hub to copy. Use `list_hubs` to find hubs and match by `title` to obtain the `id`, or take the id from the hub URL (`/hubs/{id}`). **title** (optional): Title for the new hub (max 50 characters). **description** (optional): Description for the new hub. When omitted, the source hub description is copied. <examples> Copy a hub, supplying a new title: { "hub_id": "12345", "title": "Research hub (copy)" } Copy using only the hub id (minimal body): { "hub_id": "12345" } </examples>

ActionTry it

Create file comment

Creates a new comment on a specific file. This tool allows you to add comments to files for collaboration, feedback, or documentation purposes. Comments are visible to all users with access to the file and can be used for team communication and file annotation. The message can include special characters, line breaks, and Unicode characters. The tool returns complete comment information including metadata about the comment creation, author, and timestamps. <examples> Basic file comment: <input> { "file_id": "123456789", "message": "This document looks good overall. Please review the financial projections in section 3." } </input> Multi-line structured comment: <input> { "file_id": "777888999", "message": "Review Summary:\n\nContent: Excellent\nStructure: Well organized\nFormatting: Minor issues\nCitations: Missing sources\n\nOverall: Good work, please address the citations before final submission." } </input> </examples>

ActionTry it

Create folder

Creates new folders in Box. <examples> Create folder in root: <input> { "name": "Project Documents" } </input> Create folder in specific parent: <input> { "name": "Q4 Reports", "parent_folder_id": "123456789" } </input> </examples>

ActionTry it

Create hub

Creates new collaborative hubs for organizing content around specific topics, projects, or teams. Enables the establishment of new collaborative workspaces with customizable titles and descriptions. This tool is essential for setting up new collaborative spaces where teams can organize, share, and work together on related content. Hubs serve as central gathering points for all materials related to a particular initiative or project. **Key Features:** - Creates new hubs with custom titles and optional descriptions - Establishes collaborative workspaces for team projects - Returns complete hub information upon successful creation - Supports both minimal (title-only) and detailed hub creation <examples> Create a simple hub with title only: <input> { "title": "Marketing Team Hub" } </input> </examples>

ActionTry it

Create metadata template

Creates a new enterprise metadata template. scope must be "enterprise"; each field needs type, key, and display_name. Optional template_key, hidden, copy_instance_on_item_copy, enum/multiSelect/taxonomy. Enum color_id optional (0=Yellow, 1=Orange, 2=Red, 3=Purple, 4=LightBlue, 5=DarkBlue, 6=Green, 7=Grey); omit for default Yellow (0). SDK create sends keys only; non-default colors are PATCHed after create when color_id is set. On success returns created template JSON (or JSON after color PATCH). If color PATCH fails, response still succeeds with colorApplyWarning. <examples> Minimal template with one string field: <input> { "scope": "enterprise", "display_name": "Sample contract template", "template_key": "sampleContract", "fields": [ { "type": "string", "key": "Name", "display_name": "Name" } ] } </input> <output> { "id": "f7a9891f", "scope": "enterprise_12345", "templateKey": "sampleContract", "displayName": "Sample contract template", "hidden": false, "fields": [ { "type": "string", "key": "Name", "displayName": "Name" } ] } </output> Enum field with classification colors (color_id optional per option): <input> { "scope": "enterprise", "display_name": "Data classes", "template_key": "dataClasses", "fields": [ { "type": "enum", "key": "tier", "display_name": "Tier", "options": [ { "key": "Public", "color_id": 6 }, { "key": "Internal", "color_id": 4 }, { "key": "Restricted", "color_id": 2 } ] } ] } </input> </examples>

ActionTry it

Get file content

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. **Key Features:** - Markdown representation preferred (structure preserved for LLMs); fallback to extracted text - 50MB file size limit enforcement - Clear error messages for unsupported operations <examples> Extract text content from a file: { "file_id": "123456789", } <output> { "content": [ { "type": "text", "text": "This is the extracted text content from the file..." } ] } </output> </examples>

ActionTry it

Get file details

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>

ActionTry it

Get file preview

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.

ActionTry it

Get folder details

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>

ActionTry it

Get hub details

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>

ActionTry it

Get hub items

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>

ActionTry it

Get metadata template schema

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.

ActionTry it

Get preview page

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.

ActionTry it

List file comments

Lists all comments on a specific file. Returns a paginated list of comments with configurable fields. Default fields (id, type, message, created_by, created_at) are always returned, but you can specify additional fields as needed. Supported fields include: id, type, message, created_at, created_by, modified_at, tagged_message, and any other comment-related fields supported by the Box API. Use pagination parameters (limit/offset) to handle files with many comments efficiently. <examples> Basic file comments listing: <input> { "file_id": "123456789", "limit": 50 } </input> List with specific fields: <input> { "file_id": "987654321", "fields": ["id", "message", "created_at", "created_by", "modified_at"], "limit": 100 } </input> Paginated comments listing: <input> { "file_id": "555666777", "fields": ["id", "type", "message", "tagged_message", "created_by"], "limit": 25, "offset": 50 } </input> </examples>

ActionTry it

List folder content by folder

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>

ActionTry it

List hubs

Lists all hubs accessible to the current user with pagination support. Provides an overview of available collaborative workspaces and their basic information. Hubs in Box are collaborative workspaces that organize content around specific topics, projects, or teams. This tool helps discover what hubs you have access to, making it easy to find the right collaborative space for your work. **Key Features:** - Lists all accessible hubs for the authenticated user - Supports pagination with configurable limits and markers - Returns essential hub information including ID, type, and title - Efficient retrieval with adjustable result limits (1-1000) <examples> List all accessible hubs with default settings: <input> { "limit": 50 } </input> List hubs with custom pagination: <input> { "limit": 30, "marker": "next_marker_from_previous_response" } </input> </examples>

ActionTry it

List item collaborations

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>

ActionTry it

List metadata templates

Lists available Box metadata templates so you can discover scope and templateKey for search_files_metadata. Use this first to find templates, then get_metadata_template_schema to get field keys. Call with scope "enterprise" for your org's templates or "global" for Box global templates.

ActionTry it

List tasks

Lists all tasks associated with a specific file. This tool retrieves task information including task details, message, status, and completion rule, due date from the Box platform. Tasks in Box are used to assign work to users on files, allowing for collaboration and workflow management. This tool provides access to all tasks assigned to a particular file, helping with project management and task tracking. The response includes comprehensive task details such as task type, assignee information, due dates, completion status, and any associated comments or messages. <examples> List tasks for a file: <input> { "file_id": "1234567890" } </input> </examples>

ActionTry it

Move file

Moves an existing file to another folder in Box using PUT /files/{id} (see Box API Update file). The file stays the same item (same ID); only its parent folder changes. **You must set `parent_folder_id`** to the folder ID that will become the new parent (use `"0"` for the user's root folder). Optionally set `name` to rename the file while moving. **Key features:** - Destination folder external-access guard (same as copy_file) - Optional rename via `name` <examples> Move a file into a folder: { "file_id": "123456789", "parent_folder_id": "987654321" } Move a file to the user's root folder: { "file_id": "123456789", "parent_folder_id": "0" } </examples>

ActionTry it

Move folder

Moves an existing folder to a new parent in Box using PUT /folders/{id} (Update folder). The folder keeps the same ID; only its parent changes. This is **not** for restoring items from trash. **You must set `parent_folder_id`** to the folder ID that will become the new parent (use `"0"` for the user's root folder). Optionally set `name` to rename the folder while moving. **Key features:** - External-access guard on the folder being moved and on the destination parent (same pattern as other folder write tools) <examples> Move a folder under another folder: { "folder_id": "123456789", "parent_folder_id": "987654321" } Move a folder to the user's root: { "folder_id": "123456789", "parent_folder_id": "0" } </examples>

ActionTry it

Search files keyword

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": "john.doe@company.com" } } ] } </input> </examples>

ActionTry it

Search files metadata

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.

ActionTry it

Search folders by name

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>

ActionTry it

Set file metadata

Creates or updates a metadata template instance on a file (POST when the template is not yet applied, PUT JSON Patch when it is). Use list_metadata_templates and get_metadata_template_schema first for scope, template_key, and field keys. Same tool handles both first-time application and updates.

ActionTry it

Set folder metadata

Creates or updates a metadata template instance on a folder (POST when the template is not yet applied, PUT JSON Patch when it is). Use list_metadata_templates and get_metadata_template_schema first for scope, template_key, and field keys. Same tool handles both first-time application and updates. Does not apply to the root folder (ID "0").

ActionTry it

Update file properties

Updates file metadata: name, description, tags, and collections. **Updatable fields:** - `name` - File name with extension (max 255 chars). **IMPORTANT: Always preserve the original file extension unless explicitly instructed to change it.** - `description` - File description (max 256 chars) - `tags` - Tags array (max 100) - `collections` - Collections array with format [{"id": "collection_id"}] <examples> Rename file: <input>{"file_id": "123456789", "name": "Q1-Report-2024.pdf"}</input> Update description and tags: <input> { "file_id": "987654321", "description": "Q1 2024 financial report", "tags": ["finance", "2024"] } </input> Multiple updates: <input> { "file_id": "444555666", "name": "Updated-Doc.docx", "tags": ["project"], "collections": [{"id": "98765"}] } </input> </examples>

ActionTry it

Update folder properties

Updates folder metadata: name, description, tags, and collections. **Updatable fields:** - `name` - Folder name (max 255 chars, no / \ . .. or leading/trailing spaces) - `description` - Folder description (max 256 chars) - `tags` - Tags array (max 100) - `collections` - Collections array with format [{"id": "collection_id"}] <examples> Rename folder: <input>{"folder_id": "123456789", "name": "Q1 2024 Reports"}</input> Update description and tags: <input> { "folder_id": "987654321", "description": "Q1 2024 financial reports", "tags": ["finance", "2024"] } </input> Multiple updates: <input> { "folder_id": "444555666", "name": "Project Folder", "tags": ["project"], "collections": [{"id": "98765"}] } </input> </examples>

ActionTry it

Update hub

Updates the title or description of a specific hub. This tool allows you to modify hub settings including title and description to keep hub information current and relevant. You can update one or more properties of a hub by providing the hub ID and the fields you want to change. Only the fields you specify will be updated; others remain unchanged. <examples> Update hub title: <input> { "hub_id": "12345", "title": "Updated Marketing Team Hub" } </input> Update both title and description: <input> { "hub_id": "12345", "title": "Q4 Planning Hub", "description": "Collaborative workspace for Q4 strategic planning and resource coordination" } </input> Update only description: <input> { "hub_id": "67890", "description": "Updated project description with new requirements and objectives" } </input> </examples>

ActionTry it

Update metadata template

Updates a metadata template schema (PUT /2.0/metadata_templates/{scope}/{template_key}/schema). Use scope and template_key from list_metadata_templates or get_metadata_template_schema. Each operation needs op; use camelCase in data per Box API. Shield classifications (template_key "securityClassification-6VMVochwUWo", fieldKey "Box__Security__Classification__Key"): set color in data.staticConfig.classification.colorID (0=Yellow, 1=Orange, 2=Red, 3=Purple, 4=LightBlue, 5=DarkBlue, 6=Green, 7=Grey). Top-level color_id/colorID is auto-rewritten before the API call. On success returns updated template JSON. <examples> Rename the template: <input> { "scope": "enterprise", "template_key": "sampleContract", "operations": [ { "op": "editTemplate", "data": { "displayName": "Rename template" } } ] } </input> <output> { "id": "f7a9891f", "scope": "enterprise_12345", "templateKey": "sampleContract", "displayName": "Rename template", "hidden": false, "fields": [ { "type": "string", "key": "Name", "displayName": "Name" } ] } </output> Add a string field: <input> { "scope": "enterprise", "template_key": "sampleContract", "operations": [ { "op": "addField", "data": { "type": "string", "key": "matterId", "displayName": "Matter ID" } } ] } </input> <output> { "id": "f7a9891f", "scope": "enterprise_12345", "templateKey": "sampleContract", "displayName": "Rename contract template", "fields": [ { "type": "string", "key": "counterparty", "displayName": "Counterparty" }, { "type": "string", "key": "matterId", "displayName": "Matter ID" } ] } </output> </examples>

ActionTry it

Upload file

Uploads a new file to Box. This tool creates a new file in Box using the provided text content. The file name including the extension must be provided and the extension must match the file content. Markdown uploads (e.g. .md) are regular text files like any other supported extension; use a .boxnote file name only when file_content should become a native Box Note via the notes conversion API. A parent folder ID can optionally be provided to determine where the new file should be created. The metadata details of the newly uploaded file are returned in response. If a file already exists with the same name, the tool will return an error. **Key Features:** - File creation with text content - Supported file extensions: txt, md, boxnote, html, svg, xml, csv, json, js, ts, py, sh - If the file extension is invalid, a .txt file will be created **Important:** This tool can only accept text content, to upload binary files, use the `get_upload_url` tool instead. <examples> Upload a file to Box: { "file_name": "example.md", "file_content": "#This is my example markdown file", "parent_folder_id": "0", } <output> { "content": [ { "type": "text", "text": "{"file_link": "https://example.app.box.com/file/123456789", "file_id": "123456789", "file_name": "example.md", "size": 100, "created_at": "2025-01-01T00:00:00Z"}" } ] } </output> </examples>

ActionTry it

Upload file version

Upload new file version by providing the entire file contents to Box. This tool updates an existing file's version in Box using the given file ID and content. The file ID must correspond to an existing file; otherwise, an error will be returned. Upon success, the metadata details of the updated file version are returned in the response. **Key Feature:** - Update file version with text content **Important:** This tool can only accept text content, to upload binary files, use the `get_upload_url` tool instead. <examples> upload a new file version in Box: { "file_id": "123", "file_content": "#This is my example markdown file", } <output> { "content": [ { "type": "text", "text": "{"file_id": "123", "file_name": "example.md", "size": 100, "created_at": "2025-01-01T00:00:00Z"}" } ] } </output> </examples>

ActionTry it

Who am i

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>

ActionTry it

How the Box MCP integration works

The Box MCP integration connects your Dench AI CRM directly to Box MCP, so agents can read and act on your Box MCP data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.

44 actions are available for agents to invoke on your behalf. Every call runs through Box MCP's own authorization, scoped to the account you connect.

Set up Box MCP in Dench

  1. 1

    Sign in to your Dench workspace and open Integrations.

  2. 2

    Find Box MCP and click Connect — you'll authorize access through Box MCP's own sign-in flow. No API keys or code required.

  3. 3

    Ask an agent to use Box MCP in chat, or call it from an automation.

  4. 4

    Manage or disconnect the connection any time from workspace settings.

Frequently asked questions

How does the Box MCP integration work with Dench?

The Dench Box MCP integration connects your AI CRM to Box MCP, so AI agents can work with your Box MCP data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.

What actions can AI agents perform with Box MCP via Dench?

The Box MCP integration currently exposes 44 actions, including Add items to hub, Ai extract freeform, Ai extract structured from fields, Ai extract structured from fields enhanced, Ai extract structured from metadata template, and Ai extract structured from metadata template enhanced. Agents invoke them on your behalf from chat or from automations.

Do I need to write code to connect Box MCP to Dench?

No. You connect Box MCP from your Dench workspace using Box MCP's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.

Is the Box MCP integration secure?

Connections are authorized through Box MCP's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the Box MCP connection from your workspace settings at any time.