Connect your AI agent to Box MCP
Search, retrieve, analyze, and manage enterprise content stored in Box through Box's hosted MCP server.
Set it up in Melso
- 1In Melso, open Settings → Agent Apps and hit Connect on Box MCP.
- 2Finish the OAUTH2 sign-in in the window that opens. Melso stores the connection, not your credentials.
- 3Open your agent, go to its Agent Apps tab, and allow Box MCP.
- 4Give the agent a task. It calls Box MCP itself when the work needs it.
What Box MCP gives your agent
The tools, permissions, and events Box MCP exposes — the same ones your agent can use once the app is authorized.
What you sign in with
Box MCP connects with OAUTH2.
- Client id
- Client secret
Permissions
Tools Box MCP exposes
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>
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>
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>
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>
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>
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>
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>
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>
Compare nearby apps
Other Model Context Protocol connections your agents can use.
Connect to Notion
Notion centralizes notes, docs, wikis, and tasks in a unified workspace, letting teams build custom workflows for collaboration and knowledge management
Connect to Google Docs
Google Docs is a cloud-based word processor with real-time collaboration, version history, and integration with other Google Workspace apps
Connect to DocuSign
DocuSign provides eSignature and digital agreement solutions, enabling businesses to send, sign, track, and manage documents electronically
Connect to Text to PDF
Convert text to PDF
Connect to Confluence
A tool for team collaboration and knowledge management.
Connect to SharePoint
SharePoint is a Microsoft platform for document management and intranets, enabling teams to collaborate, store, and organize content securely and effectively