Summary
Connects to Dropbox API v2 through Pipeworx's gateway infrastructure. You get five core tools: list folder contents, search by name or content, pull metadata like size and revision info, download files as text, and create folders. Part of a larger 673-source gateway, so you can either hit the standalone Dropbox endpoint or use the full Pipeworx hub and query with natural language through ask_pipeworx instead of calling tools directly. Useful when you need Claude to browse your Dropbox structure, locate files without exact paths, or pull down content for processing. Uses streamable HTTP transport rather than stdio.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
12 tools
DROPBOX_CREATE_FILE_REQUESTTool to create a new file request in Dropbox. Use when you need to request files from others by generating a unique link for uploads to a specified Dropbox folder, optionally with a deadline.4 params
Tool to create a new file request in Dropbox. Use when you need to request files from others by generating a unique link for uploads to a specified Dropbox folder, optionally with a deadline.
Parameters* required
deadlineobjectRepresents the deadline parameters for a file request.
destinationstringThe path in the user's Dropbox where uploaded files will be saved. Must be a path starting with '/'. Example: '/Homework/math'
openbooleanWhether the file request should be open by default. If true, the file request will start accepting files immediately.default: true
titlestringThe title of the new file request. Must be 1 character or more.
DROPBOX_CREATE_FOLDERTool to create a new folder at a specified path in Dropbox. Use when you need to organize files by creating a new directory. Requires the 'files.content.write' scope.2 params
Tool to create a new folder at a specified path in Dropbox. Use when you need to organize files by creating a new directory. Requires the 'files.content.write' scope.
Parameters* required
autorenamebooleanIf there's a conflict, have Dropbox automatically rename the folder. The default for this field is False.default: false
pathstringPath in the user's Dropbox to create the new folder.
DROPBOX_CREATE_PAPERCreates a new Dropbox Paper document at the specified path using HTML or Markdown content.3 params
Creates a new Dropbox Paper document at the specified path using HTML or Markdown content.
Parameters* required
contentstringContent of the paper document
import_formatstringFormat of the provided contentdefault: html
pathstringPath in Dropbox where the Paper document will be created. Do NOT include any file extension - Paper docs don't use extensions.
DROPBOX_DELETE_FILE_OR_FOLDERPermanently deletes the file or folder at the specified path in Dropbox. Use when you need to remove a specific file or folder. Requires the `files.content.write` scope.1 params
Permanently deletes the file or folder at the specified path in Dropbox. Use when you need to remove a specific file or folder. Requires the `files.content.write` scope.
Parameters* required
pathstringThe path to the file or folder to delete
DROPBOX_GET_ABOUT_METool to get information about the current user's Dropbox account. Use when you need to retrieve account details like email, name, or account type.
Tool to get information about the current user's Dropbox account. Use when you need to retrieve account details like email, name, or account type.
No parameter schema in public metadata yet.
DROPBOX_GET_TEMPORARY_LINKTool to get a one-click temporary (expiring) download link. Use when you need to share a Dropbox file directly without proxying content through this service. Requires `files.content.read` scope.1 params
Tool to get a one-click temporary (expiring) download link. Use when you need to share a Dropbox file directly without proxying content through this service. Requires `files.content.read` scope.
Parameters* required
pathstringThe path or identifier of the file to get a temporary link for. Supports Dropbox path (e.g., '/folder/file.txt'), id:..., rev:..., or ns:... notation.
DROPBOX_LIST_FILES_IN_FOLDERTool to list files and folders in a specified Dropbox directory. Use when you need to see the contents of a folder, including subfolders if recursive is true.6 params
Tool to list files and folders in a specified Dropbox directory. Use when you need to see the contents of a folder, including subfolders if recursive is true.
Parameters* required
include_deletedbooleanIf true, includes deleted (but potentially recoverable) files and folders in the listing.default: false
include_media_infobooleanIf true, includes media metadata (e.g., dimensions, location) for photo and video files.default: false
include_non_downloadable_filesbooleanIf true, includes non-downloadable files (e.g., Google Docs, Dropbox Paper) in the listing.default: true
limitintegerThe maximum number of results to return per request. Default is 2000. Max is 2000.default: 2000
pathstringThe folder path (e.g., "/europe/invoices", "" for root) or folder ID (e.g., "id:aBcDeFgH123") to list contents from.default:
recursivebooleanIf true, recursively lists contents of nested subfolders; otherwise, lists only immediate contents.default: false
DROPBOX_LIST_FOLDERSRetrieves a list of folders, files, and deleted entries from a specified Dropbox path.4 params
Retrieves a list of folders, files, and deleted entries from a specified Dropbox path.
Parameters* required
include_deletedbooleanWhether to include folders that have been deleted but may be recoverabledefault: false
limitintegerMaximum number of folder entries to return per request; an approximate upper bound.default: 2000
pathstringPath to the folder (e.g., "" for root, "/folder/subfolder", or "id:abc123xyz"). If a path string, it must start with / and not end with / or whitespace.default:
recursivebooleanWhether to include folders in nested subfolders (True) or only immediate subfolders (False)default: false
DROPBOX_MOVE_FILE_OR_FOLDERMove file or folder5 params
Move file or folder
Parameters* required
allow_ownership_transferbooleanAllow moves by owner even if it would result in an ownership transfer for the content being moved. This does not apply to copies. The default is false.default: false
allow_shared_folderbooleanIf true, allows moving shared folders. The default is false.default: false
autorenamebooleanIf there's a conflict (e.g., a file with the same name already exists at the destination), have the Dropbox server try to auto-rename the file to avoid the conflict. The default is false.default: false
from_pathstringPath in the user's Dropbox to be moved. This path is case-sensitive.
to_pathstringPath in the user's Dropbox that is the destination. This path is case-sensitive.
DROPBOX_READ_FILEDownloads a file from the specified Dropbox path, requiring `files.content.read` scope.1 params
Downloads a file from the specified Dropbox path, requiring `files.content.read` scope.
Parameters* required
pathstringThe path to search in
DROPBOX_SEARCH_FILE_OR_FOLDERTool to search for files and folders in Dropbox. Use when you need to find an item by name or content, optionally within a specific path or with other filters, and paginate through results. Example: Search for 'report.docx' in the '/finance' folder.2 params
Tool to search for files and folders in Dropbox. Use when you need to find an item by name or content, optionally within a specific path or with other filters, and paginate through results. Example: Search for 'report.docx' in the '/finance' folder.
Parameters* required
optionsobjectAdditional options for the search. If not provided, default search options will be used.
querystringThe search string. Must be 1 or more characters. Queries are case-insensitive.
DROPBOX_UPLOAD_FILEUploads a file to a specified path in the user's Dropbox, with options for handling existing files.6 params
Uploads a file to a specified path in the user's Dropbox, with options for handling existing files.
Parameters* required
autorenamebooleanIf true and a file already exists at the path, the new file will be renamed to avoid conflict.default: false
contentstringFile to be uploaded; supports various formats including images, PDFs, and text files.
modestringSpecifies how to handle the upload if a file already exists at the specified path.default: add
mutebooleanIf true, the user will not be notified of the new file via desktop or mobile notifications.default: false
pathstringPath in the user's Dropbox to save the file.
strict_conflictbooleanIf true, the upload will be rejected if the file already exists, regardless of the autorename setting.default: false
mcp-dropbox
Dropbox MCP Pack — wraps the Dropbox API v2
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
| Tool | Description |
|---|---|
dropbox_list_folder | List files and folders in a Dropbox directory. Returns names, types, sizes, and modification dates. Use when browsing folder contents or checking what's stored at a path. |
dropbox_search | Search Dropbox for files and folders by name or content. Returns matching paths, file types, and metadata. Use when you need to find a file without knowing its exact location. |
dropbox_get_metadata | Get detailed metadata for a file or folder: size, modified date, ID, sharing status, and revision info. Use before downloading or modifying to inspect properties. |
dropbox_download | Download a file from Dropbox and return its content as text plus metadata (size, type, modified date). Use to retrieve file contents for processing or inspection. |
dropbox_create_folder | Create a new folder in Dropbox at a specified path. Returns folder metadata. Use to organize files or set up directory structures. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"dropbox": {
"url": "https://gateway.pipeworx.io/dropbox/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/dropbox/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Dropbox data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
