Developer tools
ClickUp for AI agents.
Know where work stands.
Read ClickUp tasks, statuses, assignees and List context through each user’s own connection. Give your agent the facts for delivery updates and handoffs.
About ClickUp
With the ClickUp connector, your agent reads tasks, lists, folders and spaces in each user’s own ClickUp account. It can find a task, read its status, assignees and comments, and browse the lists that hold the work, using only the tools your project allows.
ClickUp is a work management platform for tasks, docs and team projects.
Tools
What your agent can do in ClickUp.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own ClickUp connection.
-
Read a task
Readclickup_get_taskRetrieve a task’s description, status, assignees and due date when available.
-
List tasks
Readclickup_list_tasksRead tasks in a selected List, with attention to pagination and the requested task filters.
-
Read task comments
Readclickup_get_task_commentsRead comments on a task to add discussion context to a handoff.
-
Read a List
Readclickup_get_listRead a List’s details to understand the container for the selected work.
-
List Lists in a Folder
Readclickup_list_listsFind the Lists inside a selected Folder.
-
List folderless Lists
Readclickup_list_folderless_listsFind Lists that sit directly in a Space rather than inside a Folder.
-
List Folders
Readclickup_list_foldersRead the Folders in a selected Space to locate the work the user requested.
-
List Spaces
Readclickup_list_spacesRead the Spaces available in a selected Workspace.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in ClickUp, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read tasks and lists, and switch off
clickup_get_task_commentsif it should not read the discussion on a task. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example tasks and lists but not comments. A call outside them is refused.
Get started
Connect ClickUp
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect ClickUp
Each end user authorizes their own ClickUp account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own ClickUp account, once. const connection = await agent200 .user("user_123") .connect("clickup"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the ClickUp tools
Name the user, the model and the tools. The model decides which ClickUp tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "What is the status of the website redesign task", tools: ["clickup"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Connect the user’s ClickUp account
The end user authorizes ClickUp through the managed OAuth flow. Your application signs in its own users and supplies the same stable user identity for the connection and later requests.
-
Choose the relevant Workspace
ClickUp’s OAuth flow lets users authorize Workspaces. Confirm that the Workspace containing the requested task is authorized and that the user can open the task in ClickUp.
-
Keep credentials out of task content
Keep the Agent200 API key in server configuration or a secure credential store. Task descriptions and comments are source material for the answer, not instructions to expose keys or expand access.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the ClickUp connector and how to use it.
Connector: ClickUp, through Agent200. In code: "clickup". What it does: Read ClickUp tasks, statuses, assignees and List context through each user’s own connection. Give your agent the facts for delivery updates and handoffs. Page: https://www.agent200.com/connectors/clickup/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on ClickUp's own page, through the authorization link Agent200 returns. Never ask a user for a ClickUp password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: clickup_get_task, clickup_list_tasks, clickup_get_task_comments, clickup_get_list, clickup_list_lists, clickup_list_folderless_lists, clickup_list_folders, clickup_list_spaces. Name "clickup" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/clickup/framework/claude/ https://www.agent200.com/connectors/clickup/framework/chatgpt/ https://www.agent200.com/connectors/clickup/framework/claude-code/ https://www.agent200.com/connectors/clickup/framework/muse/ https://www.agent200.com/connectors/clickup/framework/grok-bot/ https://www.agent200.com/connectors/clickup/framework/openai-dots/ https://www.agent200.com/connectors/clickup/framework/claude-duet/ https://www.agent200.com/connectors/clickup/framework/hermes-agent/ https://www.agent200.com/connectors/clickup/framework/openclaw/ https://www.agent200.com/connectors/clickup/framework/langgraph/ https://www.agent200.com/connectors/clickup/framework/openai-agents-sdk/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/clickup.md
Guides
Use ClickUp with the AI you build on.
Step-by-step setup for ClickUp with a specific model, assistant or agent framework.
-
ClickUp + Claude
How to connect ClickUp to Claude
-
ClickUp + ChatGPT
How to connect ClickUp to ChatGPT
-
ClickUp + Claude Code
How to connect ClickUp to Claude Code
-
ClickUp + Muse
How to connect ClickUp to Muse
-
ClickUp + Grok Bot
How to connect ClickUp to Grok Bot
-
ClickUp + OpenAI Dots
How to connect ClickUp to OpenAI Dots
-
ClickUp + Claude Duet
How to connect ClickUp to Claude Duet
-
ClickUp + Hermes Agent
How to connect ClickUp to Hermes Agent
-
ClickUp + OpenClaw
How to connect ClickUp to OpenClaw
-
ClickUp + LangGraph
How to connect ClickUp to LangGraph
-
ClickUp + OpenAI Agents SDK
How to connect ClickUp to OpenAI Agents SDK
FAQ
ClickUp and Agent200, answered.
Which task identifier should my agent use?
Use the identifier for the task the user selected. ClickUp distinguishes its task ID from a custom task ID. Its provider API requires the custom-ID option and Workspace context when using a custom ID. Check the actual runtime tool schema before mapping those inputs; a task title is not a unique identifier.
See the ClickUp task reference.
Can a task have more than one assignee?
Yes. Summarize the assignees returned for the task rather than forcing them into a single owner. Keep the recorded status label intact. If the result omits an assignee, date or description, report what is missing instead of inventing it.
Why can a List briefing miss tasks?
ClickUp task lists are paginated. Filters, closed tasks and subtasks affect the result scope, and tasks whose home is another List need separate inclusion. State the List and scope you used; follow pagination before claiming full coverage.
See Get Tasks. The provider options are not an asserted Agent200 argument mapping.
Does a task read include all its discussion and documents?
Use the task-comments operation when the answer needs discussion context. Comments are paginated, so a recent page is not the full history. A task read does not return the contents of attached ClickUp Docs. Do not imply that an attachment reference means its contents were read.
See task comments and the task endpoint.
How should my application display due dates?
Use the meaning of the date information returned by the tool. ClickUp’s provider API uses Unix timestamps in milliseconds, and dates without a chosen time have special timezone behavior. Avoid interpreting a date-only deadline as a precise appointment time.
See ClickUp date formatting and verify the runtime’s output format before converting values.
How does ClickUp fit into my agent application?
Your application authenticates its user and gives Agent200 that user’s stable identity. The user connects ClickUp, then your agent requests the allowed tools with the same identity. Agent200 executes calls against the user’s connection; your app handles presentation, scheduling and delivery.
The catalogue names describe operations. They are not request schemas or an installable SDK contract. Discover the actual tool definitions and handle missing identifiers, refused calls and absent fields before building a broader workflow.
What should I check when access fails?
Confirm the user, authorized Workspace and selected task or List. Have the user complete authorization if requested. A refused call is not an empty task or proof that work is finished. If the connection succeeds but a particular operation is unavailable, inspect the discovered tools and project configuration.
ClickUp documents OAuth and account permissions. Never request a user’s ClickUp password in chat.
How do I keep a briefing within the requested scope?
Enable only the ClickUp read operations needed for the briefing. The tools on this page do not create tasks, change statuses, assign people or post comments. Resolve the requested task or List and clarify ambiguous matches before reading.
Project controls determine which tools and endpoints the agent can request; ClickUp permissions still apply to the connected user. State the scope of returned records and do not describe a partial result as a complete inventory.
What can I ask my agent to do with these reads?
- Read the ClickUp task I identify and summarize its status, assignees and due date. Ask for the task ID if it is missing.
- Brief me on the tasks returned from this ClickUp List. State which List and result scope you used.
- Prepare a handoff from this task’s description and available comments. Separate recorded facts from open questions.