mcp-teamline
Enables MCP hosts to call the Teamline API for user authentication, task listing, creation, completion, and webhook management.
README
mcp-teamline
MCP stdio server that wraps the Teamline API so MCP hosts (Cursor, Claude, etc.) can call Teamline.
API docs: https://support.teamline.app/article/64-integrating-using-the-teamline-api
This repository is MIT-licensed. The Teamline API itself is governed by Teamline Terms of Service; using this server against Teamline means those terms apply to the API traffic.
Prerequisites
- Node.js 20 or later
Environment
Set TEAMLINE_API_KEY in the environment. Create a key at https://my.teamline.app/settings/api
The token is read only from the environment. It is never a tool argument and is never logged.
Optional: TEAMLINE_HTTP_ENCODING=json or form (default json). The official article does not document the HTTP method or encoding; this server POSTs JSON { token, ...params } by default, with form-urlencoded as a fallback.
Cursor (mcp.json)
Using the GitHub package:
{
"mcpServers": {
"teamline": {
"command": "npx",
"args": ["-y", "github:aroy314/mcp-teamline"],
"env": {
"TEAMLINE_API_KEY": ""
}
}
}
}
Fill TEAMLINE_API_KEY from your local secret store or OS environment. Do not commit a real key.
Local run
Install dependencies and compile TypeScript, then start with: node dist/index.js
Provide TEAMLINE_API_KEY in the environment when launching. After install, the bin name is mcp-teamline.
Tools
| Tool | Input | Description |
|---|---|---|
| teamline_auth_test | none | Calls Teamline auth.test and returns the authenticated user as JSON (id, name, email). |
| teamline_tasks_list | optional: limit (number), channel (#name or slackId), list (~name or id; channel required if list is set), user (@name, email, or slackId), complete (boolean; true = only completed) | Calls Teamline tasks.list. If channel and user are omitted, the API defaults to yourself. Returns the task array as JSON. |
| teamline_tasks_create | name (required); optional: description, assign (string[] of @name/email/slackId), channel, list (channel required if set), personal (boolean), due (ISO8601 or human string), notify (string[]) | Calls Teamline tasks.create. Returns the created task as JSON. |
| teamline_tasks_complete | task (required, id string) | Calls Teamline tasks.complete. Returns the completed task as JSON. |
| teamline_webhooks_create | event (required, currently only tasks_completed), url (required), name (optional) |
Calls Teamline webhooks.create to register a user-provided URL. This server registers the URL; it does not receive webhook POSTs. Returns the hook as JSON. |
| teamline_webhooks_remove | hook (required, id string) | Calls Teamline webhooks.remove. Returns the removed hook as JSON. |
If TEAMLINE_API_KEY is missing, tools return a clear error without calling the network.
License
MIT (c) 2026 Alexandre Roy. Teamline ToS apply to use of the Teamline API.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。