MCP server
Box MCP server
Box's official MCP server lets AI search and read files, ask questions across documents with Box AI, extract data and upload files.
- Official server
- Files and storage
At a glance
- Maintained by
- Box
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Box is popular with larger companies and regulated industries for storing and sharing content. Its official MCP server lets an assistant search files and folders, read content, ask questions of one or many files with Box AI, extract structured data and upload files or create folders.
The Box AI tools are notable: questions and extraction run inside Box, next to the content and its permissions, rather than sending whole documents elsewhere.
Access follows the Box user or app the server signs in as, including Box's permissions and governance settings. We connect it with an account that sees only the needed folders, and we keep upload and folder creation limited to specific destinations.
Use cases
Best business use cases
Ask across documents
Extract data
Find content
File results
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: search, read, Box AI Q&A and extraction, upload, folders, metadata, sharing, collaborations, hubs and Doc Gen.
-
who_am_iReturn details about the signed-in Box user.
-
search_files_keywordSearch files by keyword.
-
search_folders_by_nameSearch folders by name.
-
list_folder_content_by_folder_idList files, folders and web links in a folder.
-
get_file_contentReturn the content of a file.
-
ai_qa_single_fileAsk Box AI a question about one file.
-
ai_qa_multi_fileAsk Box AI a question across several files.
-
ai_extract_freeformExtract metadata from files with a plain-language prompt.
-
upload_fileUpload a new file to Box.
-
create_folderCreate a folder in Box.
Workflows
Example workflows
Compare renewal dates
-
1
Select a folder of supplier contracts.
-
2
The assistant asks Box AI for each renewal date.
-
3
It extracts dates into a table.
-
4
It flags renewals in the next 90 days.
-
5
Procurement reviews the list.
File a monthly report
-
1
An assistant prepares a monthly report.
-
2
It checks the destination folder.
-
3
It uploads the file with a clear name.
-
4
It confirms the upload.
-
5
The team is notified.
Prompts
Example prompts
“Across the contracts in this folder, list renewal dates and notice periods.”
“Find folders named "Board" and list their files.”
“Extract invoice number, date and total from these PDFs.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http --client-id YOUR_BOX_CLIENT_ID --client-secret --callback-port 8080 box https://mcp.box.com- Hosted server: https://mcp.box.com.
- Needs: OAuth 2.0. Client ID and Client Secret from Box Admin Console. Scopes root_readwrite, ai.readwrite, and docgen.readwrite (Doc Gen needs Enterprise Advanced)..
- Claude Desktop: Add as a custom connector with URL https://mcp.box.com and the Client ID and Client Secret from the Box Admin Console integration credentials.
Security
Security considerations
-
Limit folders
Connect an account or service user that sees only the folders a task needs.
-
Start with reading
Begin with search and read access. Add write actions one at a time.
-
Sensitive files
Box governance and permissions apply. Keep classification labels in place.
-
Keep a record
Log which files the assistant opens and changes.
Related servers
Servers that pair well with it
Dropbox
Dropbox's own MCP server lets AI list, search and read files, convert them to markdown and create, move, share and delete files. In beta.
Google Drive
Google's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
OneDrive
Microsoft's OneDrive MCP server, part of its Work IQ preview, lets AI find, read, create, move, share and delete files in OneDrive.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- Document automation Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
- Customer portals A secure place where your customers upload documents, check status, pay and message your team.
Solutions
View all solutions- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- AI document processing Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
- Contract review assistant Highlight unusual clauses, missing terms and deviations from your standard positions, so reviewers focus where it matters.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
Industries
View all industries- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Insurance Claims intake, document and photo processing, policy knowledge assistants and customer portals for brokers and insurers.
- Healthcare Patient booking, intake forms, internal knowledge assistants and admin automation for clinics and care providers.
- Finance and accounting Client portals, document collection, invoice and receipt processing, and reporting for accounting firms and finance teams.
- Tax and compliance services Client portals, document checklists, case queues and deadline tracking for tax preparers and compliance firms.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
Case studies
View all case studiesGuides and articles
View all guides and articlesAI models
View all ai models- Claude Sonnet 5 Anthropic's balance of speed and intelligence: a strong everyday model for assistants, document work, tool calling and coding.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Command A+ Cohere's enterprise flagship for multimodal, multilingual agent tasks, with 48 languages, tool calling, JSON output and open weights under Apache 2.0.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- OCR OCR, or optical character recognition, is technology that turns text in images and scanned documents into machine-readable text.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained by Box.
Box's own AI features, which the server uses to answer questions and extract data from files.
Yes. It acts as the signed-in user or app.