Feature Requests

It'd be dope if clickup AI would support https://modelcontextprotocol.io/ . With that its agent could instantly integrate with a ton of tools without you having to do first party integrations in the first place. Some tools like cursor.ai just allow you to paste in an MCP link and bam, you have it in your agent. Support this ONE thing and save time integrating all the others. Let your users do the job and give them the power to integrate properly.

I would like to suggest introducing a feature that allows exporting details (e.g., space, folder, list, etc.) related to the use of automations and AI. This would make it easier to locate the automations being used and quickly understand which ones have the greatest impact on costs. Currently, there are two separate functionalities that cannot be correlated and lack the ability to export or filter: Usage Details / Usage Breakdown with total numbers Log of executed automations Similar to: https://feedback.clickup.com/feature-requests/p/feature-usage-list

Since Clickup is deep in openai ecosystem, please upgrade the underlying model powering Clickup Brain's searching and writing with GPT-5 full version instead of 4o. Searching is still very bad with Brain and it's writing could be improved heavily.

It would be beneficial if the AI Notetaker had better integration with Microsoft Teams. Our organization uses Teams for their virtual meetings. Because the ClickUp AI Notetaker is not authenticated with our domain it is considered an external user. Microsoft Teams puts the Notetaker into the lobby and someone has to accept it into the meeting. Once accepted into the meeting it appears like another person in the meeting. This is very confusing to anyone in our organization who doesn't use ClickUp and it just seems strange to have a notetaker represented as a person in the meeting. Asks: Please develop some way that the AI Notetaker can authenticate so it doesn't end up in the lobby. Please develop a cleaner approach to having the Notetaker take notes during meetings instead of being represented as another person in the meeting.

The get_chat_channels tool returns DM channels with only type , visibility , creator , and created_at — there is no members or counterparty field. For an agent, this makes it impossible to identify which DM channel corresponds to which user without probing messages in every channel. Repro: 1. Authenticate against mcp.clickup.com/mcp as a user with several DMs 2. Call clickup_get_chat_channels 3. All DM entries list the viewer as creator with no indication of the other party Impact: - An agent cannot send a DM to a named user without enumerating every DM channel and checking its messages for a user_id match. - Today's workaround: the user manually seeds a DM in the ClickUp UI, then the agent probes each DM's messages looking for the one with fresh activity. - Scales poorly (O(n) API calls per user lookup), and is brittle on empty or cold DMs. Suggested fixes (pick any): 1. Include members: [user_id, …] (or an explicit counterparty_user_id for DMs) in the get_chat_channels response. 2. Add a clickup_find_or_create_dm_channel tool that takes a user ID and returns the DM channel ID (creating it if missing). 3. Allow clickup_send_chat_message to accept a recipient_user_id alongside (or instead of) channel_id , auto-resolving/creating the DM. This mirrors Slack's chat.postMessage , which accepts a user ID as channel and auto-opens the DM. Context: Hit while integrating the first-party mcp.clickup.com/mcp server into an internal MCP Manager. Happy to test any proposed fix.

DOCX is currently not allowed as a format to upload to the clickup chat. It would be good to be able to upload docx-like word documents, not just txt and pdf

It would be great to be able to use AI to quickly generate clean, and cool looking whiteboards. Currently the AI Brain in whiteboard only generates images, and they are all cut off. Instead, i'd like to ask it to "pull all tasks from this board as headers with unique colors, and put descriptions as sub sticky notes". That way I could create a quick org chart, or view of specific tasks quickly, efficiently, and in a cool looking way. On some other tools this involves importing .json and .csv data which most LLM/AI tech can work with. If I could simply copy and paste in such formats and choose my template look or describe it then it would save tons of time in the long run. No current workaround to generate formatted whiteboard material. I can almost get there by importing .csv or .json as tasks using import or AI Brain. Then I have to drag in each tasks. However, once I try to do any whiteboarding the AI just generates faulty images instead of editable structures in a useful format. Final goal, open whiteboard, ask AI to pull in tasks I've already got of a tag type from X project, tell it to build a color coded structure using bubbles at the top and stickies below it (or from template example), and presto it builds a structure. Example attached. I've use a different tool and AI to do this with prompts so it's very possible. Giving users a few preset prompts and styles would solidify this as useful for all sorts of purposes in the whiteboard tool.

It would be awesome for Brain to be able to read attachments that are uploaded in the Resources card in a space. Docs, images, etc; instead of having to upload them into Brain chat. That would unlock at lot of capacity for Brain to get better on-demand context into things and perform better.

ClickUp Brain currently appears to rely on a single AI model. I would like the ability to connect and use multiple AI models/providers within ClickUp Brain, so teams can choose the best model for each use case (quality, cost, speed, privacy, compliance). Key capabilities requested: Multi-provider connections: Allow admins to connect different AI providers/models (for example OpenAI, Anthropic, Google, etc.). Model selection controls: Let users (or workspace admins) select which model ClickUp Brain uses, either: * as a default per workspace/space/list, and/or * per action (summarize task, draft content, extract action items, analyze docs, etc.). Policy and governance: Admin controls for which models are allowed, where they can be used, and optional restrictions for sensitive Spaces/Lists. Quality and cost optimization: Enable teams to route lightweight tasks to cheaper/faster models, and complex reasoning tasks to stronger models. Auditability: Provide visibility into which model was used for an output (for troubleshooting, QA, and compliance). Value/Impact: Better outcomes across different Brain workflows (summaries, drafting, analysis). Flexibility for organizations with strict security/compliance requirements. Cost control by matching the model to the complexity of the request.

Overview: Persistent memory would allow ClickUp Brain to remember user-defined preferences, shorthands, and workflow rules across sessions—similar to features in ChatGPT, manus.im and other standout AI tools. This would significantly enhance workflow efficiency and user experience. Use Case Example: As a user managing multiple “Inbox” lists across different Spaces (e.g., General, Business, Relationships), I want to quickly capture tasks, notes, and ideas into the correct list using custom shorthands (e.g., “Inbox: [my entry]”, “Business Inbox: [my entry]”, “gi: [my entry]”). Currently, ClickUp Brain does not retain these preferences between sessions, requiring me to repeat instructions or clarify context each time, which is very inefficient. Benefits: - Frictionless Capture: Users can define and reuse custom shorthands for rapid task entry, reducing cognitive load and saving time. - Personalized Workflows: Persistent memory enables tailored automation, such as routing items to the correct list or applying user-specific rules without repeated setup. - Consistency: Ensures that workflow processes remain consistent, even as users switch devices or return after a break. - User Empowerment: Allowing users to view, update, or delete their stored preferences gives them control and transparency, increasing trust in the AI assistant. Feature Suggestion:- Enable persistent, user-manageable memory for “Brain Max" (or indeed ClickUp). - Allow users to set, review, and update their own shorthands, rules, and preferences. - Provide an interface for managing these settings, similar to prompt libraries or automation dashboards. Impact: This feature would streamline daily workflows, reduce repetitive setup, and make ClickUp Brain a true productivity partner—especially for power users and teams with complex/ personalised processes.