Dropbox MCP: Two Official Servers, One in Beta
Yes — Dropbox has an official MCP server. In fact there are two. The remote MCP server (mcp.dropbox.com/mcp, in open beta since March 2026) lets any MCP-compatible AI tool read and write the files in your Dropbox. A separate Dash MCP server adds AI-powered search across all your connected company content. So if you’re searching “Dropbox MCP,” the connection you want almost certainly exists.
The thing worth knowing before you set it up: an MCP server hands your files to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches Dropbox for you, nothing fires when a file lands in a folder, and nothing runs while the chat is closed. Here’s exactly what the Dropbox MCP does, how to turn it on, where it stops — and what to use when you want Dropbox work that runs on its own.
Dropbox is one of many — the complete list of MCP servers covers every app that ships one, grouped by category.
What the Dropbox MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, and others — talk to an outside app through a shared interface. Dropbox maintains two official servers:
- Remote MCP server (
mcp.dropbox.com/mcp, open beta since March 2026) — gives an MCP-compatible AI read and write access to your Dropbox files: browse folders, pull metadata, extract text, search, create, copy, move, delete, and manage shared links. - Dash MCP server (
github.com/dropbox/mcp-server-dash, local/stdio) — a read-only search server that lets an AI query across everything Dash indexes, including connected tools like Google Workspace, Slack, and GitHub.
For most people the first one is what “Dropbox MCP” means. With it connected, an AI client can:
- Find files — “which folder has the signed Acme contract?” answered by searching your live Dropbox by name or content.
- Read documents — pull the text out of a PDF, doc, or spreadsheet (up to about 5 MB) and summarize or answer questions about it.
- Create and organize — make a folder, drop in a file, move or copy things, and clean up without opening the Dropbox app.
- Share and collect — generate a shared link or set up a file request straight from the chat.
It’s genuinely useful for ad-hoc work: ask where something is, read it, tidy a folder, share a file — all in one conversation.
How to set up the Dropbox MCP server
The remote server is the quick path — no code, no hosting:
- In your AI client’s connector settings, add a remote MCP server pointing at
https://mcp.dropbox.com/mcp. - Authorize it against your Dropbox account through the OAuth prompt — you’re granting the AI the same access your own login has.
- Confirm the tools appear in the client, then start a chat and ask it to find or read a file.
Dropbox supports this across Cursor, Claude Web, Claude Code, ChatGPT Web, and ChatGPT Codex. (ChatGPT needs Developer Mode turned on first.) The Dash server runs locally instead — you clone the repo and add it to your client’s MCP config with an OAuth key — and it’s read-only, built for searching company content rather than editing files. For non-developers, the remote file server is the one you want.
Where the Dropbox MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch Dropbox; it waits for you to ask.
- No triggers. A new file landing in a shared folder, a contract getting signed, a file request coming back filled — none of these can start anything through MCP. There’s no “when this shows up in Dropbox, do that.”
- It’s one app at a time. The Dropbox MCP knows Dropbox. Getting a new upload into a Slack channel, a CRM record, and a tracking sheet means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. OAuth tokens, refresh, and the blast radius of read/write access to your files are all on you.
So the Dropbox MCP is a great way to ask Dropbox things, read documents, and make one-off changes. It is not a way to make Dropbox run — to have work happen on a schedule or in reaction to an event, across the other tools a file touches.
Running Dropbox work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Dropbox natively — no MCP server to host, no OAuth plumbing to maintain — and to the ~260 other apps it supports natively, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Dropbox work happens whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a new file lands in a client folder → extract the key details, log a row in your tracking sheet, and post a heads-up to the
#accountsSlack channel — automatically, the moment it arrives. - Every morning → check for files that have been sitting in an “Unsorted” folder over a week and email you the list to review.
- When a file request comes back filled → rename the file to your naming convention, move it into the right project folder, and update the record in your CRM.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Dropbox connection and everything downstream.
If you just want to search and read your files from a chat, Dropbox’s official MCP server is the right tool and it’s free to connect. If you want Dropbox to actually do things — on a trigger, on a schedule, across every app a file flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does Dropbox have an official MCP server?
Yes — two. The remote MCP server at mcp.dropbox.com/mcp (open beta since March 2026) gives MCP-compatible AI tools read/write access to your files, and a local Dash MCP server (github.com/dropbox/mcp-server-dash) provides read-only AI search across your connected company content.
Is the Dropbox MCP server free? Connecting the remote MCP server is free; you’re authorizing an AI client against your existing Dropbox account and its access. You still need whatever Dropbox plan your files live on.
Can the Dropbox MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Dropbox work across apps, you need a workflow tool like Carly rather than an MCP server.
Can I connect Dropbox to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Dropbox for you and lets you build the automation in plain language — describe what you want to happen and it wires up the files and the other apps involved, with no server to host and no code to write.
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
