You can connect ClickUp to Claude using the Model Context Protocol (MCP), and once it’s connected, Claude can list what’s due in a space, draft a task with the right assignee and status, or summarize a doc without you opening the ClickUp app. This guide covers what ClickUp’s MCP server does, both ways to connect it — directly or through a gateway — and one thing worth knowing before you try: ClickUp’s OAuth isn’t currently open to every client that asks.

What the ClickUp MCP server actually does

ClickUp publishes a remote MCP server at mcp.clickup.com. It exposes your tasks, docs, and spaces as tools Claude can call directly, so prompts like these work against your real workspace:

  • “What’s due in the marketing space this week?”
  • “Create a task for the launch checklist, assign it to me, status in progress.”
  • “Summarize the onboarding doc in the engineering space.”
  • “Which tasks are blocked and who’s waiting on them?”

Claude reads and writes through the same permissions your ClickUp account already has — it isn’t a read-only export, it’s your workspace’s actual tasks, docs, and spaces, queried and edited on demand.

The catch: ClickUp’s OAuth isn’t open to every client yet

Some servers in gate’s directory — Notion, Todoist, Airtable — let any AI client register itself and go straight through a one-click OAuth consent screen. ClickUp’s MCP endpoint is one of a handful where that isn’t the case today: the vendor’s OAuth currently only admits clients ClickUp has allow-listed in advance, rather than opening registration to any client that shows up. In practice, that can mean a connection attempt from a new or less-common client fails at the authorization step, even though the server itself is real and documented.

This is the same gap covered in MCP OAuth scopes explained: a server supporting OAuth in principle isn’t the same claim as every client being able to walk through it today. If you hit an “unauthorized client” error connecting ClickUp, that’s the most likely reason — not a mistake in your setup. See the unauthorized client error, explained for the general pattern and workarounds. Whether a given client can connect changes as vendors expand their allow-list over time, so it’s worth checking again later if it doesn’t work on your first attempt.

Option 1: Connect ClickUp to Claude directly

If the client you’re using is one ClickUp currently admits, the setup is:

  • Open Claude’s connector or MCP settings.
  • Add a remote server pointing at ClickUp’s MCP endpoint.
  • Sign in with your ClickUp account when prompted — standard OAuth, so Claude never sees your ClickUp password, and you can revoke access from ClickUp’s own account settings at any time.

That’s enough if Claude is the only AI client you use with ClickUp. The tradeoff shows up once you add a second client — Cursor for pulling task context into code work, ChatGPT for a quick status check — or a second person on the team: each one needs its own attempt at the same OAuth step, with the same chance of hitting the allow-list wall independently.

Option 2: Connect it once, through a gateway

If you’re already juggling more than one MCP server or more than one AI client, wiring each pair directly gets old fast — that’s the connection sprawl covered in what an MCP gateway is. The idea is to connect ClickUp (and everything else) to one gateway URL, then point every AI client at that single URL instead of reconfiguring each one and re-running the OAuth step per client.

With gate specifically, connecting ClickUp looks like this: add gate’s gateway URL to Claude once, then pick ClickUp from the ClickUp server page in the directory and sign in the same way you would directly. gate’s catalog tracks each server’s currently verified connectivity — including cases like this one, where a vendor’s OAuth is still allow-listed — so you know what to expect before you start, instead of finding out mid-flow. See the full list of servers on the MCP servers page.

What to check before you connect a task tracker

A ClickUp account usually spans more than the one space you had in mind when you connect it — every team, every folder, every private doc. A few things worth checking before or right after you connect:

  • Which spaces and folders are in scope? An MCP connection to ClickUp typically covers every space your account can reach, not just the one you’re currently working in. Know what’s in scope before you hand Claude a broad prompt like “summarize everything that’s overdue.”
  • Can it create and edit tasks, not just read them? ClickUp’s MCP tools generally cover writes as well as reads — a task created or reassigned by a prompt is a real change your teammates will see, the same write-tool caution covered in MCP tool idempotency if a retry ever double-creates one.
  • Who else on the team connects it? If more than one person wires up ClickUp to their own client, a shared, revocable setup beats everyone holding their own grant — the same question covered in MCP access control for teams.

You can run a quick, no-signup check on any server’s tool list with gate’s free MCP security scanner, which looks for prompt injection and hidden instructions in tool descriptions before you rely on a server day to day.

Troubleshooting the connection

  • “Unauthorized client” or the OAuth screen never appears. Most likely the allow-list issue above — the client you’re using may not be one ClickUp currently admits for this endpoint.
  • Sign-in succeeds but Claude can’t see a space you know exists. ClickUp’s tools respect your user’s own team membership; a space that lives under a team you’re not part of won’t show up any more than it would in the ClickUp app itself.
  • Tools disappear after a ClickUp update. Remote servers can change their tool list without warning. If you’re connected through a gateway, that kind of change is exactly what drift detection is meant to catch — see how MCP rug pulls work for why a one-time review isn’t enough.
Where gate fits: gate’s directory lists each server’s currently verified connectivity — one-click OAuth, key-based, or allow-listed like ClickUp — so you know what kind of setup to expect before you start. Every server is scanned for prompt injection before it goes live, and every call goes into a plain-language log. See the full gateway at /mcp-gateway.

The bottom line

Connecting ClickUp to Claude with MCP is a normal OAuth flow when the client you’re using is one ClickUp currently allows — direct if it’s your only client, or once through a gateway if you want the same task, doc, and space access shared across every AI client on the team. If the connection fails at the authorization step, that’s worth reading as “not allow-listed yet” rather than a broken setup, and worth trying again as ClickUp opens this up over time.