ClickUp
效率与工作流by Polaralias
借助完整生产力工具直接管理 ClickUp 中的项目、任务和文档,支持跨工作区搜索任务、生成状态报告、跟踪工时,并查看文档层级与成员信息。
什么是 ClickUp?
借助完整生产力工具直接管理 ClickUp 中的项目、任务和文档,支持跨工作区搜索任务、生成状态报告、跟踪工时,并查看文档层级与成员信息。
核心功能 (41 个工具)
pingEcho request for connectivity checks.
healthReport server readiness and enforced safety limits.
tool_catalogueEnumerate all available tools with their annotations.
workspace_capability_snapshotExpose cached ClickUp capability probes for this session.
workspace_listList accessible ClickUp workspaces (teams). Use when you need workspace IDs before exploring spaces.
space_list_for_workspaceList spaces for a workspace by workspaceId. Use search when you only know workspace names.
folder_list_for_spaceList folders within a ClickUp space. Use when you already know spaceId.
list_list_for_space_or_folderList lists inside a space or folder by ID. If you only know names, resolve them first with resolve_path_to_ids.
workspace_overviewSummarise workspace metrics and recent spaces/folders/lists when you have a workspaceId.
workspace_hierarchyFetch nested hierarchy (spaces, folders, lists) for one or more workspaces. Use this to browse structure without task data.
hierarchy_resolve_pathResolve workspace/space/folder/list names into IDs. Use before tools that require IDs.
member_list_for_workspaceList members in a workspace by teamId. Use when you already know the workspaceId.
member_resolveResolve member identifiers (id, email, username) into member records for a workspace.
member_search_by_nameFuzzy search member names to find member IDs.
task_assignee_resolveTranslate assignee references into suggested member IDs for tasks.
space_tag_listList tags configured for a space using spaceId.
reference_link_listList public ClickUp API reference links.
reference_page_fetchFetch a public ClickUp API reference page from a link returned by reference_link_list.
task_searchStructured task search with filters. Use when you have listIds/tagIds; returns tasks across lists.
task_search_fuzzyFuzzy task search from natural language when you do not have precise filters.
task_search_fuzzy_bulkBatch fuzzy task searches for multiple natural language prompts.
task_status_reportSummarise task status and priority for a workspace, space, folder or list without returning full task lists.
task_risk_reportSummarise overdue and at-risk tasks within a workspace, space, folder or list. Subtasks are included by default; use includeSubtasks to focus on parent tasks and inspect isSubtask/parentId in results to understand hierarchy.
task_readFetch task details including createdDate/updatedDate fields derived from ClickUp timestamps. Subtask cues (isSubtask, parentId, hasSubtasks, subtaskCount) are included; check them before claiming there are no subtasks. GET /task/{task_id}
task_list_for_listList tasks in a list. Tasks linked from other lists are included by default (include_timl=true). Outputs include createdDate derived from ClickUp date_created and hierarchy cues (isSubtask, parentId, hasSubtasks, subtaskCount). Always review hasSubtasks/subtaskCount before asserting there are no subtasks. Results are paginated and may span multiple pages; iterate via the page input to retrieve additional pages. GET /list/{list_id}/task
task_comment_listRetrieve task comments for a taskId.
list_custom_field_listList custom fields configured for a list by listId.
doc_listList documents within a workspace using filters.
doc_readFetch document metadata and pages for a docId.
doc_pages_readFetch selected document pages by docId and pageIds.
doc_page_listList page hierarchy for a document by docId.
doc_page_readFetch a single document page by docId and pageId.
doc_searchSearch document content across a workspace. Use doc_page_read for specific pages.
doc_search_bulkBatch document searches when you need several queries processed together.
task_time_entry_listFetch time entries for a taskId, including total duration.
time_entry_currentRetrieve the current running timer for the workspace.
time_entry_listList time entries with filters. Accepts ISO 8601 or epoch boundaries; include taskId when focusing on a single task.
time_report_for_tagAggregate logged time for a tag across the workspace. Use space_tag_list to discover tags, and includeSubtasks to control whether child task time is counted.
time_report_for_containerAggregate time for a workspace, space, folder or list using containerId + containerType. Resolve IDs with resolve_path_to_ids, list_workspaces/spaces/folders/lists, and set includeSubtasks to clarify hierarchy handling.
time_report_for_contextAggregate time for a task, list (including filtered views), space or workspace. Use search_tasks or task_list_for_list to source listId/taskId before calling. Subtask handling is explicit via includeSubtasks.
time_report_for_space_tagAggregate time for a tag within a space using spaceId. Use space_tag_list to pick the tag and includeSubtasks to control hierarchy.
README
clickup-mcp
Standalone Python/FastMCP server for ClickUp with direct HTTP transport, static API-key auth, and no tunnel sidecar.
Highlights
- Default MCP endpoint:
http://localhost:3004/mcp - Default health endpoint:
http://localhost:3004/health - Supports
CLICKUP_MCP_API_KEY,MCP_API_KEY, orMCP_API_KEYS - Preserves existing ClickUp write controls such as
WRITE_MODE,WRITE_ALLOWED_SPACES, andWRITE_ALLOWED_LISTS
Reference Docs
- Tool reference contains the full public tool inventory and parameter schemas (79 tools).
- Configuration reference explains the supported env vars, auth modes, ports, storage, and deployment knobs.
Configuration
- Copy
.env.exampleto.env - Fill in the required values:
CLICKUP_API_TOKENCLICKUP_TEAM_IDorTEAM_IDCLICKUP_MCP_API_KEY
Common optional settings:
CLICKUP_MCP_PORTCLICKUP_MCP_HOST_PORTCLICKUP_MCP_PATHWRITE_MODEWRITE_ALLOWED_SPACESWRITE_ALLOWED_LISTSAPI_KEY_MODE
Docker Compose note:
- If a secret contains a literal
$, escape it as$$in.env
Run Locally
python scripts/run_server.py serve
python scripts/run_server.py doctor
python scripts/run_server.py url
The local helper serves streamable HTTP on MCP_HOST / MCP_PORT / MCP_PATH.
Run With Docker Compose
docker compose up -d --build
docker compose ps
docker compose logs -f
The included docker-compose.yml publishes the ClickUp MCP server on port 3004 by default and joins the external reverse_proxy network.
Add To A Shared MCP Compose Project
Use this service in a larger compose stack when you want one project containing multiple MCP servers:
services:
clickup-mcp:
build:
context: /path/to/clickup-mcp
dockerfile: Dockerfile
restart: unless-stopped
env_file:
- /path/to/clickup-mcp/.env
environment:
MCP_HOST: 0.0.0.0
MCP_PORT: "3004"
MCP_PATH: /mcp
ports:
- "3004:3004"
networks:
- reverse_proxy
networks:
reverse_proxy:
external: true
If you do not need host port publishing because you are fronting the service with another internal proxy, you can omit the ports section.
MCP Client Connection
- URL:
http://<host>:<port>/mcp - Header:
Authorization: Bearer <your-api-key>
Repository Notes
- Tool definitions are loaded from
tool_manifest_clickup.json - The runtime talks directly to ClickUp API v2 and v3
- Health responses identify the server as
clickup-mcp
常见问题
ClickUp 是什么?
借助完整生产力工具直接管理 ClickUp 中的项目、任务和文档,支持跨工作区搜索任务、生成状态报告、跟踪工时,并查看文档层级与成员信息。
ClickUp 提供哪些工具?
提供 41 个工具,包括 ping、health、tool_catalogue 等。
相关 Skills
表格处理
by anthropics
围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。
✎ 做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
Word文档
by anthropics
覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。
✎ 搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。
相关 MCP Server
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。