todo-full
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., "@todo-full Add a task: buy groceries tomorrow"
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.
todo-full · 串起手册要点的完整示例
一个 todo list,两条路对比实现,接真 DeepSeek。用一份可运行代码把 MCP 全套手册的要点串起来。
覆盖的要点
三原语:MCP server 里 Tools + Resources + Prompts 都有
function calling:MCP client 把工具翻译成 DeepSeek 的 tools,跑工具循环
JSON-RPC 原始消息:
VERBOSE=1打印底层 tools/call 请求与响应手搓 vs MCP:
manual_way.py是不用 MCP 的对照组换个 Host 也能跑:同一个 server 经
.mcp.json接进 Claude Code,代码一行不改
Related MCP server: Enhanced Todoist MCP Server Extended
文件
文件 | 是什么 |
| 共用的 SQLite 数据库层(两条路都调它) |
| 路 A:MCP server,三原语齐全 |
| 路 A:MCP client + DeepSeek 工具循环(主程序) |
| 路 B:手搓 prompt + 解析 + 分发(对照组) |
| 代码 ↔ 手册要点的逐条对照 |
| uv 项目清单与锁文件,统一管理依赖 |
跑起来
需要 uv 和一个 DeepSeek API key。
# 首次运行前安装依赖(uv run 也会自动同步,这一步可省略)
uv sync
# 路 A:MCP(主示例)
DEEPSEEK_API_KEY=sk-xxx uv run mcp_client.py
# 路 A + 看底层 JSON-RPC 消息
DEEPSEEK_API_KEY=sk-xxx VERBOSE=1 uv run mcp_client.py
# 路 B:手搓对照
DEEPSEEK_API_KEY=sk-xxx uv run manual_way.pymcp_client.py 会自动把 mcp_server.py 当子进程拉起(stdio),你不用单独启动它。
依赖统一声明在 pyproject.toml 里,uv run 会按 uv.lock 自动建虚拟环境并安装,无需手动管理。
配合 Claude Code 使用
除了跑 mcp_client.py(自己当 Host+Client),也可以让 Claude Code 直接当 Host 连这个 server —— 同一个
mcp_server.py 一行不用改,这正是「server 不关心对面是谁」的体现。
.mcp.json 已经把它注册好了:
{
"mcpServers": {
"todo": {
"command": "uv",
"args": ["run", "--directory", "/path/to/mcp-primer", "mcp_server.py"]
}
}
}在项目目录里启动 claude 即可自动加载,/mcp 面板能看到连接状态和三原语。用法:
Tools:直接说「加一个任务:写周报」,模型会调
mcp__todo__add_taskResources:
@todo:todos://all引用全部任务;todos://{status}是模板资源,@todo:todos://done/@todo:todos://pending同样可读(模板资源不会出现在资源列表里,但能直接取)Prompts:
daily_review也会一并暴露,具体入口见/mcp面板
这条路看不到 JSON-RPC 原始消息
VERBOSE=1 是 mcp_client.py 自己在应用层打印的,走 Claude Code 这条路不生效。Claude Code 的
claude --debug mcp --debug-file <path> 只给连接生命周期的摘要,不含协议报文:
[DEBUG] MCP server "todo": Successfully connected (transport: stdio) in 313ms
[DEBUG] MCP server "todo": Connection established with capabilities: {"hasTools":true,...}
[DEBUG] ToolSearchTool: selected mcp__todo__add_task实测这份日志里 grep jsonrpc / tools/call / tools/list 命中数为 0。/mcp 面板同理,是状态面板不是协议探针。
想看原始报文,就在 Host 和 server 之间插一层 tee —— stdio 传输本质就是两条管道,原样转发不影响功能:
#!/bin/bash
# mcp_server_debug.sh,记得 chmod +x
DIR="$(cd "$(dirname "$0")" && pwd)"
mkdir -p "$DIR/mcp_logs"
tee -a "$DIR/mcp_logs/in.jsonl" \
| uv run --directory "$DIR" mcp_server.py \
| tee -a "$DIR/mcp_logs/out.jsonl"把 .mcp.json 的 command 指向这个脚本("command": "/path/to/mcp_server_debug.sh", "args": []),重连后
in.jsonl(Host→server)和 out.jsonl(server→Host)会记下全部方法的报文 —— 不只是 tools/call,
initialize、tools/list、resources/read 都在里面,比 VERBOSE=1 只覆盖 tools/call 更全。
日志是追加写且含任务内容,记得加进 .gitignore。
说明
数据库文件
todos.db首次运行自动创建在项目目录,重启后任务不丢。若访问 DeepSeek 需要代理,脚本已带
httpx[socks],设置ALL_PROXY即可。mcp 锁在 1.x(
mcp>=1.28,<2):2.0 是大改版、API 不同,示例按 1.x 写。
Available Tools
3 toolsadd_taskC
添加一条待办任务。
Inputs: title (required). Returns: result
complete_taskA
把指定 id 的任务标记为完成。
Inputs: task_id (required). Returns: result
delete_taskA
删除指定 id 的任务。
Inputs: task_id (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct action on a task: adding, completing, or deleting. There is no overlap or ambiguity between them.
All tools follow the same verb_noun pattern: add_task, complete_task, delete_task. Naming is uniform and predictable.
With only 3 tools, the set is minimal but each tool serves a clear purpose in the todo domain. The count is well-scoped and appropriate.
The set includes create, complete, and delete operations but lacks a way to list or retrieve tasks. This is a significant gap since agents cannot view existing tasks, making the tool surface incomplete for a todo workflow.
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
ADHD-friendly task management MCP server for ChaTodo: organize tasks, lists, and priorities.
MCP server for generating rough-draft project plans from natural-language prompts.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that provides tools and resources for managing a coding project's todo list, allowing users to view, add, update, and delete todo items with details like priority, status, and tags.1-
- AlicenseBqualityDmaintenanceA comprehensive MCP server that provides full integration between Claude and Todoist, enabling task, project, section, and label management through 24 different tools with the complete Todoist API.306MIT
- FlicenseNot gradedqualityDmaintenanceAn AI-powered TODO list MCP server with categories, timeboxing, and due dates, enabling natural language task management.-
- FlicenseNot gradedqualityDmaintenanceMCP server that provides tools to create and list tasks by consuming a REST API, allowing LLMs to manage a TODO list via natural language.-