worklog-telegram
Logs work entries to daily Markdown files and sends summaries to Telegram automatically at 11 PM or on demand.
README
Work log → Telegram
MCP server that logs what you got done throughout the day, one Markdown file per day grouped by project, and sends the day's log to Telegram — nightly on a schedule or on demand.
1. Install
git clone https://github.com/Rithvickkr/code-logs.git
cd code-logs
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
2. Configure Telegram
Copy-Item .env.example .env
Then fill in the two values:
- Message @BotFather →
/newbot→ copy the token. - Send your new bot any message (a bot can't start the conversation).
- Open
https://api.telegram.org/bot<TOKEN>/getUpdatesand copyresult[0].message.chat.id. - Put both in
.envasTELEGRAM_BOT_TOKENandTELEGRAM_CHAT_ID.
.env is gitignored. If the same variables are set in the real environment,
those win.
3. Register the MCP server
Run from the repo root, at user scope so every project logs to the same place:
claude mcp add --scope user worklog -- .\.venv\Scripts\python.exe .\server.py
Use absolute paths if your client needs them.
4. Tell Claude to log as it works
Add to ~/.claude/CLAUDE.md:
The `worklog` MCP server keeps one Markdown file per day, grouped by project.
- After each meaningful unit of work lands, call `log_work` with a one-line
past-tense summary, and `project` set to the working directory's name.
- One call per item. Don't batch a session into one entry, don't log routine
steps, don't ask permission first.
- Call `send_summary` only when asked for the log.
5. Schedule the nightly send
powershell -ExecutionPolicy Bypass -File .\register-task.ps1
Registers WorkLogSummary at 23:00 daily. Override with -At "22:30" or
-TaskName "...".
Start-ScheduledTask -TaskName "WorkLogSummary" # run it now
Get-ScheduledTaskInfo -TaskName "WorkLogSummary" # last run + result
Unregister-ScheduledTask -TaskName "WorkLogSummary" -Confirm:$false
6. Send on demand
Ask Claude — "send me today's log", "send it" — or from the shell:
python send.py --dry-run # print, don't send
python send.py --date 2026-08-01 # re-send an older day
python send.py # send today's
Tools
| Tool | What it does |
|---|---|
log_work(entry, project) |
Files a bullet under ## <project> in logs/<date>.md |
send_summary(day) |
Posts that day's log to Telegram |
Log format
# 2026-08-02
## project-one
- 09:14 Rebuilt the beat cards
- 11:02 Added project grouping to the daily log
## project-two
- 14:30 Fixed the logo glyph
Entries are appended to their project's section; a section is created the first time that project is logged.
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。