# How to connect ClickUp to Grok Bot

> Use Grok Bot with Agent200 to read ClickUp task statuses, assignees and due dates. Build clear handoffs through the user’s own connection.

- Page: https://www.agent200.com/connectors/clickup/framework/grok-bot/
- Connector: [ClickUp](https://www.agent200.com/connectors/clickup.md)
- Framework: Grok Bot
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect ClickUp to Grok Bot with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/clickup/framework/grok-bot/

1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Grok Bot's settings themselves: never ask for it in chat and never write it into files you share.
2. Make sure ClickUp is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs.
3. Add Agent200's MCP server to Grok Bot: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Grok Bot's exact menus or commands.
4. The first ClickUp request returns an authorization link if the user has not connected ClickUp yet: show it to them and continue once they have approved access on ClickUp's own page.
5. Check it works with this request: "Using Agent200, read the ClickUp task identified in this chat. Give me a status briefing with its assignees, deadline and description. Ask me to identify the task if needed. Do not use browser data or modify anything."
   What should come back:
   - The selected task is identified clearly.
   - The answer preserves its returned status, includes all returned assignees and reports its due date when available.
   - Missing data and access failures are stated clearly; no ClickUp records or comments are changed.
6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in ClickUp, then retry.

## Overview

Use Grok Bot for an on-demand briefing from a selected ClickUp task. Attach the Agent200 connector to the conversation and name the task you want. This keeps the source of the answer explicit when the Bot also has browser access or other connected apps.

Begin with one task the connected user can access. The ClickUp catalogue on this page is read-only: a briefing does not create, assign, complete or delete work. Discover the available tools and use their returned schemas before running the test.

Product reference: [Grok Bot documentation](https://docs.x.ai/grok-bot/computer-and-apps). For task identity and response scope, see [ClickUp’s task reference](https://developer.clickup.com/reference/gettask).

- **Connector:** [ClickUp](https://www.agent200.com/connectors/clickup/)
- **Works with:** Grok Bot · Agent app, through MCP
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [8 tools](https://www.agent200.com/connectors/clickup/framework/grok-bot/#tools)
- **MCP server:** `https://api.agent200.com/mcp/`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **ClickUp enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a ClickUp account.** They approve access once, on ClickUp's own page.
- **Grok Bot, with custom MCP servers allowed.** Grok Bot comes with SuperGrok, Grok Business seats and paid Cursor plans. On a team, the admin's connector policy must allow the Agent200 server.

## Connect ClickUp to Grok Bot

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. You add it to Grok Bot in the next step, as "Authorization: Bearer <your key>". One key covers ClickUp and every other connector enabled for your project. Keep it out of chats and source control.

Create an API key: https://agent200.com/platform/apikeys/

### Step 2: Open the custom connector form

In Grok Bot, open **Connect apps** from the sidebar and choose **Add a custom connector** at the bottom.

### Step 3: Fill in the server and your key

Enter the name Agent200, pick Type **Remote HTTPS**, enter the server URL and add one HTTP header: `Authorization` with the value `Bearer` followed by your key. Leave Client ID empty, then choose **Add plugin**.

File `Add a custom connector`:

```text
Name:          Agent200
Type:          Remote HTTPS
Server URL:    https://api.agent200.com/mcp/
HTTP headers:  Authorization: Bearer YOUR_AGENT200_API_KEY
```

### Step 4: Attach Agent200 in a chat

In a Bot chat, type `@` and attach Agent200 to the task. Custom servers are account-wide, so every Bot on the account can use it.

### Step 5: Connect your ClickUp account

The first time you ask Grok Bot for something in ClickUp, Agent200 returns an authorization link. Open it and approve access on ClickUp's own page. Agent200 stores the connection and keeps it working; your password never reaches Grok Bot or Agent200.

## Test your connection

Ask: "Using Agent200, read the ClickUp task identified in this chat. Give me a status briefing with its assignees, deadline and description. Ask me to identify the task if needed. Do not use browser data or modify anything."

What should come back:

- The selected task is identified clearly.
- The answer preserves its returned status, includes all returned assignees and reports its due date when available.
- Missing data and access failures are stated clearly; no ClickUp records or comments are changed.

Use a task the connected user can open in the authorized Workspace. Check the runtime schema if using a custom task ID. Report missing data and preserve the task’s returned status label.

## ClickUp tools Grok Bot can call

- **Read a task** (`clickup_get_task`, read): Retrieve a task’s description, status, assignees and due date when available.
- **List tasks** (`clickup_list_tasks`, read): Read tasks in a selected List, with attention to pagination and the requested task filters.
- **Read task comments** (`clickup_get_task_comments`, read): Read comments on a task to add discussion context to a handoff.
- **Read a List** (`clickup_get_list`, read): Read a List’s details to understand the container for the selected work.
- **List Lists in a Folder** (`clickup_list_lists`, read): Find the Lists inside a selected Folder.
- **List folderless Lists** (`clickup_list_folderless_lists`, read): Find Lists that sit directly in a Space rather than inside a Folder.
- **List Folders** (`clickup_list_folders`, read): Read the Folders in a selected Space to locate the work the user requested.
- **List Spaces** (`clickup_list_spaces`, read): Read the Spaces available in a selected Workspace.

## How it works

1. **You ask Grok Bot.** In your own words, for something in ClickUp.
2. **Grok Bot picks a tool.** It sees the ClickUp tools on the Agent200 MCP server and calls the one the request needs.
3. **Agent200 runs the call.** With your own ClickUp connection, within the tools and scopes your project allows.
4. **Grok Bot answers.** It gets the result back from the MCP server and uses it in its reply or its next step.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's ClickUp account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and ClickUp enforces what its API grants.

## Troubleshooting

### The task cannot be found or read

Check the selected task and authorized ClickUp Workspace. Distinguish native task IDs from custom IDs and use the inputs your tool actually supports. Report a refused call instead of guessing a task or a successful result.

### The answer names only one person or changes the status meaning

Compare the answer with the returned record. Keep every returned assignee and the recorded status label. A missing field is not evidence that a task is unassigned or complete.

### The List summary seems incomplete

Check pagination and the task filters available in the runtime. State the result scope and avoid treating one page as the full List. See [ClickUp’s List task reference](https://developer.clickup.com/reference/gettasks).

## FAQ

### How do I know the answer came from this connector?

Name Agent200 and the selected ClickUp task in the request, and inspect the tool activity. A browser visit or a response from a different connector does not verify the Agent200 path. Check that the returned task is the one you requested.

## Use ClickUp with another framework

- [ClickUp + Claude](https://www.agent200.com/connectors/clickup/framework/claude.md)
- [ClickUp + ChatGPT](https://www.agent200.com/connectors/clickup/framework/chatgpt.md)
- [ClickUp + Claude Code](https://www.agent200.com/connectors/clickup/framework/claude-code.md)
- [ClickUp + Muse](https://www.agent200.com/connectors/clickup/framework/muse.md)
- [ClickUp + OpenAI Dots](https://www.agent200.com/connectors/clickup/framework/openai-dots.md)
- [ClickUp + Claude Duet](https://www.agent200.com/connectors/clickup/framework/claude-duet.md)
- [ClickUp + Hermes Agent](https://www.agent200.com/connectors/clickup/framework/hermes-agent.md)
- [ClickUp + OpenClaw](https://www.agent200.com/connectors/clickup/framework/openclaw.md)
- [ClickUp + LangGraph](https://www.agent200.com/connectors/clickup/framework/langgraph.md)
- [ClickUp + OpenAI Agents SDK](https://www.agent200.com/connectors/clickup/framework/openai-agents-sdk.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
