Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Dida Todo Agent Add a task for quarterly report due next Friday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Dida365（滴答清单）MCP Server + Agent Skill，让 AI Agent 用自然语言管理你的待办事项。
核心是一个规则引擎：通过可配置的路由规则，自动将自然语言任务分配到正确的项目、设定优先级和标签，避免 AI 自由发挥导致分类混乱。
不再依赖 AI 的"直觉"来分类任务。通过 Routing Profile 定义明确规则：
项目路由：为每个 Dida365 项目定义用途、正例、反例和优先级，语义匹配 + 优先级裁决
优先级策略：基于截止时间、阻塞性、关键交付等维度设定优先级（0/1/3/5），规则独立于项目名称
标签管理：自动匹配已有标签；新标签与任务合并确认，并通过任务 tags 字段 inline 写入
路由锁定：每次写操作必须携带当前 routing revision，配置过期时自动重新读取，防止错误分类
示例路由配置：
分类顺序：
1. 个人事务和生活提醒 → 个人提醒项目
2. 影响结果的工作、领导要求或关键交付 → 重要工作项目
3. 不重要且近期没有截止时间的工作 → 非紧急工作项目
4. 其余日常工作 → 一般工作项目
优先级规则（独立于项目）：
- 紧急、阻塞或 24 小时内的关键交付 = 5
- 近期普通交付 = 3
- 可延后的规划 = 1
- 日常生活提醒 = 0所有状态变更操作都经过两步确认：
Prepare：服务端返回 5 分钟有效、绑定请求参数的一次性 confirmation token
Confirm：用户明确确认后，Agent 才用该 token 提交操作
适用于：完成任务、删除任务、创建带新标签的任务、保存路由配置等。Dida365 Open API 的独立标签创建端点不可靠，因此新标签不单独调用 POST /tag。
Client Secret 和 OAuth Token 只存 OS Keyring，不落盘、不进日志、不进聊天记录。
Related MCP server: Todoist MCP Server
┌─────────────────────────────────────────────┐
│ Agent Framework │
│ (OpenClaw / Claude Desktop / Cursor / ...) │
├─────────────────────────────────────────────┤
│ Skill (dida-todo-agent) │
│ 自然语言理解 · 规则匹配 · 确认交互 │
├─────────────────────────────────────────────┤
│ MCP Server (dida365-mcp) │
│ OAuth · 凭证 · 路由校验 · 任务 CRUD │
│ 确认令牌 · 操作日志 · 并发冲突检测 │
├─────────────────────────────────────────────┤
│ Dida365 Open API │
│ api.dida365.com/open/v1 │
└─────────────────────────────────────────────┘MCP Server：规则引擎的执行层。负责 OAuth、凭证存储、路由配置校验、任务读写、确认令牌、操作日志和并发冲突检测。通过标准 stdio MCP 协议与宿主 Agent 通信。
Agent Skill：规则引擎的决策层。负责自然语言理解、项目路由匹配、优先级判定、标签匹配和用户确认交互。适配任何支持 MCP 的 Agent 框架。
cd dida-todo-agent
uv sync --frozen --extra dev.venv/bin/dida365-mcp-admin configure-app按提示输入 Dida365 开放平台的 Client ID 和 Client Secret。凭证只保存在操作系统 Keyring 中，不要粘贴到聊天或提交到 README、Agent 配置文件。
启动 MCP 服务后调用 start_oauth，工具返回授权 URL。在浏览器中打开 URL 完成授权，然后调用 auth_status 验证授权确实成功。
标准 stdio 启动配置：
{
"command": ".venv/bin/python",
"args": ["-m", "dida365_mcp.server"],
"cwd": "."
}服务端预期暴露 16 个工具（MCP tools）。不同 Agent 框架只需映射 command、args 和 cwd；不要把本机绝对路径、令牌或密钥提交到配置文件。
将 skill/ 目录复制到 Agent 框架的技能目录中。以 OpenClaw 为例：
cp -r skill/ ~/.openclaw/skills/dida-todo-agent/参考 Routing Profile Guide 编写你的路由配置，通过 save_routing_profile 工具写入。路由配置定义了项目用途、优先级策略和标签规则。
dida-todo-agent/
├── src/dida365_mcp/ # MCP Server
│ ├── server.py # MCP 工具入口 + _parse JSON 修复
│ ├── credentials.py # OS Keyring 凭证存储
│ ├── oauth.py # OAuth 2.0 回调流程
│ ├── dida_client.py # Dida365 API 客户端
│ ├── routing.py # 路由配置校验
│ ├── confirmations.py # 确认令牌管理
│ ├── ledger.py # 操作日志
│ └── ...
├── skill/ # Agent Skill
│ ├── SKILL.md # 技能定义（路由决策、确认流程）
│ └── references/ # 适配器契约、行为用例、路由指南
├── tests/ # 测试套件
└── scripts/ # OAuth 授权辅助脚本uv run pytest -q # 运行测试
uv run ruff check src tests # 代码检查
uv run mypy src # 类型检查MIT
Inputs: no named parameters. Returns: object
Inputs: request (required). Returns: object
Inputs: confirmation_token (required). Returns: object
Inputs: request (required). Returns: object
Inputs: request (required). Returns: object
Inputs: request (required). Returns: object
Inputs: no named parameters. Returns: object
Inputs: task_id (required), project_id (required). Returns: object
Inputs: no named parameters. Returns: object
Inputs: no named parameters. Returns: object
Inputs: request (required). Returns: object
Inputs: profile (required), routing_revision (required). Returns: object
Inputs: query (required). Returns: object
Inputs: no named parameters. Returns: object
Inputs: request (required). Returns: object
Inputs: no named parameters. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 16 tools
Tool names clearly differentiate actions on tasks, tags, projects, routing, and auth. However, 'confirm_action' is ambiguous and could overlap with other action tools. Overall, most tools have distinct purposes.
Most tools follow a verb_noun pattern with snake_case (e.g., list_tags, create_task, save_routing_profile). A few exceptions like 'auth_status' (noun_noun) and 'start_oauth' (verb_noun but less conventional) break the pattern but are still clear. Consistency is high but not perfect.
16 tools is reasonable for a todo agent with extended features like authentication, routing profiles, and tags. The number is slightly above the typical ideal range but still manageable and each tool serves a specific function.
The set covers core task operations (CRUD, move, complete) but lacks update and delete for tags, and lacks project creation/update/delete. Routing profile operations are present but missing delete. The 'confirm_action' tool suggests a confirmation mechanism missing in other workflows. Several gaps exist.
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Turn user requests and support messages into tasks and tell users what shipped, from any AI agent.
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane.
