DailyBot MCP
Enables Littlebird to read and submit DailyBot check-ins through the DailyBot CLI.
README
DailyBot MCP
A small local MCP server that lets Littlebird read and submit your DailyBot check-ins through the installed DailyBot CLI.
Requirements
- Python 3.10+
uv- DailyBot CLI 3.8+, authenticated as the user whose check-ins Littlebird should access
Verify DailyBot first:
dailybot --version
dailybot status --auth
If needed, authenticate with:
dailybot login
Install
From this repository directory, install dependencies:
uv sync
Run
For manual background operation:
./mcpctl start
./mcpctl status
./mcpctl logs # Ctrl-C stops following logs, not the server
./mcpctl stop
Runtime state and logs are stored under the ignored .run/ directory.
To run in the foreground instead:
uv run dailybot_mcp.py
The MCP endpoint is available only on your machine at:
http://127.0.0.1:8765/mcp
This server is localhost-only; it does not provide a remote or hosted endpoint.
Connect Littlebird
- Open Settings > Integrations in Littlebird.
- Add a custom MCP server.
- Enter
http://127.0.0.1:8765/mcpas the server URL. - Enable the integration for the chat or routine that needs DailyBot.
Tools
list_checkins(date: str | None = None) -> dict[str, Any]
get_checkin(checkin_id: str) -> dict[str, Any]
get_checkin_history(checkin_id: str, from_date: str, to_date: str, search: str | None = None, limit: int | None = None) -> dict[str, Any]
submit_checkin(checkin_id: str, answers: list[str], response_date: str | None = None, confirmed: bool = False) -> dict[str, Any]
list_checkinslists pending and completed check-ins for one date.get_checkinreturns a check-in's configuration and ordered questions.get_checkin_historyreturns responses DailyBot provides over any arbitrary inclusive date range, optionally filtered bysearchand capped bylimit.submit_checkinsubmits answers in question order only whenconfirmed=Trueafter you explicitly approve them.
Dates use YYYY-MM-DD. History results follow your DailyBot account permissions.
Development
Tests mock DailyBot and never contact a live account:
uv run python -m unittest -v
Troubleshooting
- DailyBot is not on
PATH: ensuredailybot --versionworks in the same shell used to start the server. - DailyBot is not authenticated: run
dailybot login, then verify withdailybot status --auth. - Littlebird cannot connect: confirm the server process is still running and the URL is exactly
http://127.0.0.1:8765/mcp. - Port already in use: stop the process using port
8765before starting this server.
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。