Read, browse, and search Dropbox files through MCP tools with PDF, DOCX, and text extraction.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
One-click editor setup isnβt available for this listing yet β we donβt have a confirmed install command, and weβd rather show nothing than point your editor at the wrong package or host. Follow the projectβs own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Cindyloo Dropbox MCP Server.
list_filesList files and folders in a Dropbox directory.
search_filesSearch for files by name.
read_fileRead the full content of a file.
get_file_infoGet detailed metadata about a file.
search_file_contentSearch for text within specific files.
cindyloo-dropbox-mcp-server MCP server gives an MCP-compatible agent read access to files stored in Dropbox. It can browse directory contents, find files by name, return file metadata, read file content, and search for text inside selected files. The server does not provide Dropbox write operations; its documented access is limited to reading files and metadata.
Text extraction covers PDF files through PyPDF2, DOCX and DOC documents through document-processing support, and common text-based formats including TXT, Markdown, Python, JavaScript, HTML, CSS, JSON, and CSV. This makes the server suitable for retrieving source documents, examining structured text, or locating terms in a set of known files.
The server runs locally as a Python process and communicates with an MCP client. A Dropbox access token authenticates requests to the connected Dropbox account. The token must have the files.metadata.read and files.content.read permissions described in the setup instructions.
Its tools operate on Dropbox paths and return results to the requesting agent. Directory listing and filename search can limit the number of returned items. File reads can also limit the number of characters, while content searches accept a list of files and can include surrounding context for each match.
Python 3.10 or later and a Dropbox account with an access token are required. Create a Dropbox app with scoped access, enable metadata-read and content-read permissions, and generate a token from the app settings. Store that value in DROPBOX_ACCESS_TOKEN; avoid committing it to source control.
Install the project with pip install -e ., or install the documented dependencies manually: mcp, dropbox, pydantic, PyPDF2, and python-docx. Run the server with python dropbox_server.py. For Claude Desktop, add a server entry to claude_desktop_config.json with the Python command, the path to dropbox_server.py, and the token in the entry's environment configuration. Smithery deployments also read the same environment variable.
cindyloo-dropbox-mcp-server MCP server exposes these tools:
list_files lists files and folders in a supplied directory, or the Dropbox root when no path is given. It supports a maximum-item limit.search_files searches Dropbox for filenames and can filter results by formats such as PDF, DOCX, or TXT.read_file returns the content of a file by path, with an optional character limit. A limit of zero requests unlimited output.get_file_info returns detailed metadata for a specified file.search_file_content looks for a query within a supplied list of file paths and can return configurable context around matches.The documented implementation is read-only, so it should not be used when an agent needs to upload, edit, move, or delete Dropbox content. Large file reads may need an explicit length limit because the default response size is 5,000 characters. Content extraction depends on the supported file formats and the included extraction libraries. Keep the Dropbox token in environment variables or another secure secret store, and consider using the minimum app permissions needed for the deployment.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/cindyloo-dropbox-mcp-server)<a href="https://allmcps.com/mcp/cindyloo-dropbox-mcp-server"><img src="https://allmcps.com/api/badge/cindyloo-dropbox-mcp-server?style=directory" alt="Cindyloo Dropbox MCP Server on AllMCPs" /></a>