Skip to main content
Glama
hsgui

Daily Work MCP Server

by hsgui

Daily Work MCP Server

一个用于记录、查询和总结每日工作内容的本地 MCP Server,基于 FastAPI + FastMCP + SQLite 实现。

运行前准备

  1. 安装依赖:

    conda create -n daily-work-mcp python=3.11 -y
    conda activate daily-work-mcp
    pip install -r requirements.txt
  2. 初始化数据库(首次运行必须执行):

    python scripts/init_db.py

启动方式

启动 HTTP API(可选)

uvicorn app.main:app --reload

默认监听 http://127.0.0.1:8000,包含以下 REST 接口:

  • POST /entries:新增工作内容

  • GET /entries:按 daily/weekly 查询

  • GET /entries/search:全文搜索

  • GET /entries/export:导出 JSON 或 CSV

  • GET /entries/summary:最近 N 天标签聚合

  • GET /entries/reminder:检查今日是否已有记录

  • GET /tags / POST /tags:标签管理

启动 MCP Server

python scripts/run_mcp_server.py

默认以 STDIO transport 运行;如果需要通过 HTTP/Streamable HTTP 暴露端口,可改用:

python scripts/run_mcp_server.py --transport streamable-http --host 127.0.0.1 --port 8888

脚本在 HTTP/Streamable 模式下会自动启用 stateless HTTP,即 /mcp 端点无需任何 Session/Cookie 即可访问,方便 IDE 直接连到 http://127.0.0.1:8888/mcp。 手工调试时记得同时声明 Accept: application/json, text/event-stream,例如:

curl -N \
  -H "Accept: application/json, text/event-stream" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":"1","method":"ping","params":{}}' \
  http://127.0.0.1:8888/mcp

该脚本会调用 app/mcp/server.py 中的 mcp.run() 并注册全部工具:

  • record_work_entry:新增条目

  • list_work_entries:按日/周查询

  • search_work_entries:关键字检索

  • summarize_recent_work:标签汇总

  • check_today_recorded:今日提醒状态

  • list_tags / create_tag:标签列表与新增

MCP 客户端连接该进程后即可直接调用上述工具。

使用示例

  • 新增条目(REST):

    curl -X POST http://127.0.0.1:8000/entries \
         -H "Content-Type: application/json" \
         -d '{"description":"排查登录问题","tags":["infra/login"]}'
  • 查询本周条目(REST):

    curl "http://127.0.0.1:8000/entries?range=weekly"
  • MCP 调用:在支持 MCP 的客户端中,将 scripts/run_mcp_server.py 作为 Server 入口,即可在会话中调用 record_work_entrylist_work_entries 等工具。

更多需求说明见 requirements.md

-
security - not tested
F
license - not found
-
quality - not tested

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hsgui/daily-work-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server