tasks-mcp
A lightweight task management MCP server that enables CRUD operations on tasks stored in a single JSON file, including listing, creating, updating progress, and setting priorities.
README
tasks-mcp — Task Management MCP Server
架构总览
tasks-mcp 是一个轻量级任务管理系统,核心数据为单文件 JSON index.json,提供两种接入方式:
用户(飞书/CC) → [MCP Client / CLI] → index.json
↑
claudetalk 直接写 (phone-archive)
数据文件
index.json— 核心数据存储,Record<id, entry>格式的单 JSON 文件- 每个 entry 字段: status, summary, created_at, updated_at, type, source, priority, progress
文件清单
| 文件 | 说明 |
|---|---|
src/tasks-mcp.ts |
MCP stdio 服务器,7 个 tools |
cli.py |
Python CLI,7 个子命令 |
index.json |
数据存储(已附带全部 task 数据) |
.project-type |
项目类型标记 |
MCP Server(src/tasks-mcp.ts)
运行方式
node --experimental-strip-types src/tasks-mcp.ts
暴露的工具
| 工具 | 参数 | 说明 |
|---|---|---|
tasks_list |
status?, type?, limit? | 列出任务,默认 active (pending+in_progress),默认 20 条 |
tasks_create |
summary, type?, source?, priority? | 创建 pending 任务,自动编号 |
tasks_mark_done |
task_id | 标记完成 |
tasks_delete |
task_id | 永久删除 |
tasks_get |
task_id | 查单个任务 |
tasks_set_progress |
task_id, notes, start? | 更新进度,自动设为 in_progress |
tasks_set_priority |
task_id, priority | 设置优先级 |
JSON-RPC 协议
MCP stdio transport,JSON-RPC 2.0 over stdin/stdout。
initialize 响应:
{
"protocolVersion": "2024-11-05",
"capabilities": { "tools": {} },
"serverInfo": { "name": "tasks-mcp", "version": "0.1.0" }
}
Python CLI(cli.py)
子命令
| 命令 | 参数 | 说明 |
|---|---|---|
list |
--type |
列出 active 任务 |
create |
summary, --type, --source, --priority, --action |
创建任务 |
start |
query |
标记进行中 |
mark-done |
query |
标记完成 |
set-progress |
query, notes |
更新进度 |
set-priority |
query, priority |
设置优先级 |
status |
--type |
统计概览 |
query 支持 task id 精确匹配或关键词模糊匹配。
示例
python cli.py list
python cli.py create "写文档" --type chore --source manual --priority low
python cli.py mark-done 2026-07-05/001-some-task
python cli.py set-progress 001 "50% done"
index.json Schema
"2026-07-05/001-task-name": {
"status": "pending | in_progress | completed",
"summary": "任务摘要(≤80字符)",
"created_at": "ISO 8601",
"updated_at": "ISO 8601 | null",
"type": "task | bug | feature | research | chore | reference",
"source": "claudetalk | ops-daemon | cc | manual",
"priority": "low | medium | high | critical",
"progress": "自由文本进度笔记 | null"
}
依赖
- MCP Server: Node.js 22+ (需要
--experimental-strip-types) - CLI: Python 3.10+
- 无第三方 npm/pip 依赖
注册方式
MCP Server 在 .mcp.json 中注册:
"tasks-mcp": {
"type": "stdio",
"command": "node",
"args": ["--experimental-strip-types", "/path/to/tasks/src/tasks-mcp.ts"]
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.