mlo-mcp

mlo-mcp

MCP server that enables AI agents to manage tasks in the MyLifeOrganized (MLO) Windows desktop app locally via its command-line interface, providing tools for listing, searching, adding, updating, and syncing tasks without any cloud dependency.

Category
访问服务器

README

mlo-mcp

MCP server for the MyLifeOrganized (MLO) Windows desktop app. AI agents (Claude Code, Codex, Cursor, Claude Desktop — anything that speaks MCP over stdio) manage your MLO task tree by driving mlo.exe's undocumented command line locally. No cloud API, no account, your data never leaves the machine.

  • 12 tools: list/search/get tasks, contexts, single/atomic-outline add, update/complete/uncomplete/delete, QuickSync, cloud status
  • Writes never touch your data file: the server runs a local cloud-sync endpoint, queues changes as sync deltas, and MLO's own merge logic applies them via QuickSync — the app keeps running, and the append-only delta log is the durable record of every change (see docs/mcp-cloud.md, including the one-time proxy wiring that routes the app's sync to the local endpoint)
  • Ships four customizable GTD skills (/mind, /inbox, /weekly + standing conventions) for any SKILL.md-capable agent

Requirements

  • Windows with MyLifeOrganized desktop installed
  • Node 22+ (that's all — the repo ships a self-contained bundle; no package manager needed)

Install

The only required setting is MLO_DATA_FILE — the path to your .ml profile. Try it against a copy of your profile first if you're cautious; writes are applied by MLO's own sync merge, and every change is kept as a delta in the local message log.

Any MCP client (via npx, straight from GitHub — no npm registry)

{
  "mcpServers": {
    "mlo": {
      "command": "npx",
      "args": ["-y", "github:govza/mlo-mcp"],
      "env": { "MLO_DATA_FILE": "C:\\path\\to\\your.ml" }
    }
  }
}

npx caches the GitHub install; pin a tag (github:govza/mlo-mcp#v0.2.0) for reproducibility, and re-run with a newer tag to update.

Claude Code

Either register directly:

claude mcp add mlo -e MLO_DATA_FILE=C:\path\to\your.ml -- npx -y github:govza/mlo-mcp

or install as a plugin (also ships the GTD skills; updates via /plugin update):

/plugin marketplace add govza/mlo-mcp
/plugin install mlo@govza

The plugin reads MLO_DATA_FILE from your environment — set it once, user-level:

[Environment]::SetEnvironmentVariable("MLO_DATA_FILE", "C:\path\to\your.ml", "User")

Skills (any agent)

The GTD skills install with the open agent-skills CLI — one command covers Claude Code, Codex, Cursor, and the rest of the SKILL.md ecosystem:

npx skills add govza/mlo-mcp    # update: npx skills update · remove: npx skills remove

Claude Code users who install the plugin above get the skills bundled with it instead. See skills/ for what they do and how to customize them.

From a clone (no npx)

git clone https://github.com/govza/mlo-mcp
claude mcp add mlo -e MLO_DATA_FILE=C:\path\to\your.ml -- node C:\path\to\mlo-mcp\mcp-server\dist-bundle\mlo-mcp.js

Configuration

MLO_DATA_FILE is required; optional vars (MLO_EXE_PATH, MLO_CLOUD_PORT, MLO_CLOUD_STATE_DIR, …) are documented in mcp-server/README.md.

Documentation

mcp-server/ Tools reference, configuration, development, tests
docs/ The reverse-engineered mlo.exe CLI, XML & .ml binary formats, server architecture, MLO task model
skills/ Customizable GTD skills (Claude Code, Codex, any SKILL.md-capable agent)

Everything in docs/ was verified empirically against MLO 15.x on Windows — MLO's CLI is largely undocumented, so the quirk catalog there is the map of what actually works.

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选