quickmemo-mcp
QuickMemo MCP 服务器 📝⚡
QuickMemo MCP 是一个简洁、极简且独特的模型上下文协议(MCP)服务器,为 AI 助手提供快速、结构化的便签和上下文记忆引擎。
QuickMemo 使用官方 Python MCP SDK 构建,代码干净整洁,以优雅、零冗余的代码库展示了全部三种核心 MCP 原语——工具、资源和提示。
🌟 核心亮点
⚡ 极简且零冗余:不到 150 行干净、可读的 Python 代码。
🎯 全部 3 种 MCP 原语:
工具:保存、列出、搜索、筛选、检索和删除上下文记忆。
资源:实时 Markdown 摘要(
memo://all)和动态遥测(memo://stats)。提示词:现成的提示模板,用于笔记回顾和每日站会生成。
🔒 零配置要求:使用本地持久化 JSON 存储(
~/.quickmemo/memos.json或自定义路径)。🚀 市场与注册中心就绪:预配置了
smithery.yaml和Dockerfile,可一键部署到 Smithery 和 Glama。
Related MCP server: mindmap-mcp-server
📁 项目结构
quickmemo-mcp/
├── docs/ # Learning documentation & reports
│ ├── EXISTING_MCP_EXPERIENCE.md # Hands-on write-up evaluating Context7 & Playwright
│ └── MCP_FUNDAMENTALS.md # Complete MCP protocol & architecture guide
├── src/
│ └── quickmemo/ # MCP Server package (<150 LOC)
│ ├── __init__.py # Package exports
│ ├── __main__.py # Executable entrypoint
│ └── server.py # Core server (Tools, Resources, Prompts)
├── tests/
│ ├── demo_client.py # Live interactive demonstration script
│ └── test_server.py # Pytest unit & integration test suite
├── Dockerfile # Containerized deployment manifest
├── LICENSE # MIT License
├── pyproject.toml # Package configuration & dependencies
├── README.md # Quickstart & user documentation
└── smithery.yaml # Smithery registry manifest📐 架构概览
+-------------------------------------------------------------------------------+
| MCP CLIENT |
| (Claude Desktop / Cursor IDE / Antigravity / Custom AI) |
+-------------------------------------------------------------------------------+
▲
│ JSON-RPC 2.0 (stdio)
▼
+-------------------------------------------------------------------------------+
| QUICKMEMO MCP SERVER |
| |
| [TOOLS] [RESOURCES] [PROMPTS] |
| • add_memo • memo://all (Digest) • review_notes |
| • list_memos • memo://stats (JSON) • daily_standup |
| • search_memos |
| • get_memo / delete_memo |
+-------------------------------------------------------------------------------+
│
▼
Local JSON Storage Engine
(~/.quickmemo/memos.json)🛠️ MCP 原语目录
1. 工具(模型控制的函数)
工具名称 | 参数 | 描述 |
|
| 保存新的便签或片段,可附带类别和标签。 |
|
| 列出已保存的便签,可附带类别和标签筛选。 |
|
| 检索特定便签的完整内容和元数据。 |
|
| 在标题、内容、标签和类别中执行关键字搜索。 |
|
| 按 ID 删除便签。 |
| 无 | 清空便签存储。 |
2. 资源(动态上下文流)
资源 URI | MIME 类型 | 功能 |
|
| 所有已存储便签的格式化动态 Markdown 摘要。 |
|
| 实时统计(便签总数、类别分布、标签分布)。 |
3. 提示(预设计的工作流模板)
提示名称 | 参数 | 功能 |
|
| 将已保存的便签综合为关键要点和可执行的检查清单。 |
| 无 | 将最近的便签转换为标准的 3 部分每日站会报告。 |
🚀 快速入门与安装
选项 1:使用 uv 进行本地设置(推荐)
# Clone the repository
git clone https://github.com/your-username/quickmemo-mcp.git
cd quickmemo-mcp
# Install dependencies and package in editable mode
uv pip install -e .
# Run test suite
uv run pytest -v
# Run the interactive demo
uv run python tests/demo_client.py选项 2:直接通过 CLI 运行
# Run server over stdio
quickmemo🔌 客户端配置
Claude Desktop
将 QuickMemo 添加到您的 claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"quickmemo": {
"command": "uvx",
"args": ["--from", "quickmemo", "quickmemo"]
}
}
}Cursor IDE
在工作区中添加 .cursor/mcp.json:
{
"mcpServers": {
"quickmemo": {
"command": "quickmemo"
}
}
}☁️ 部署到 Smithery / Glama
此仓库已通过 smithery.yaml 和 Dockerfile 预配置为 Smithery 注册中心。
通过 Smithery CLI 安装
npx -y @smithery/cli install quickmemo --client claude手动注册中心部署
将您的仓库推送到 GitHub。
访问 Smithery.ai 并登录。
导入您的 GitHub 仓库。Smithery 会自动检测
smithery.yaml并部署您的 MCP 服务器。
🧪 测试
运行自动化测试套件:
uv run pytest -v输出:
tests/test_server.py::TestMemoStore::test_add_and_get PASSED [ 12%]
tests/test_server.py::TestMemoStore::test_list_and_filter PASSED [ 25%]
tests/test_server.py::TestMemoStore::test_search PASSED [ 37%]
tests/test_server.py::TestMemoStore::test_delete_and_clear PASSED [ 50%]
tests/test_server.py::TestServerTools::test_tool_workflow PASSED [ 62%]
tests/test_server.py::TestServerTools::test_clear_memos_tool PASSED [ 75%]
tests/test_server.py::TestServerResourcesAndPrompts::test_resources PASSED [ 87%]
tests/test_server.py::TestServerResourcesAndPrompts::test_prompts PASSED [100%]
============================== 8 passed in 1.10s ==============================📚 交付物与学习文档
📖 现有 MCP 动手评估:
docs/EXISTING_MCP_EXPERIENCE.md📘 MCP 架构与基础指南:
docs/MCP_FUNDAMENTALS.md💻 交互式实时演示脚本:
tests/demo_client.py⚙️ Smithery 配置:
smithery.yaml
📄 许可证
MIT 许可证 © 2026 QuickMemo MCP 贡献者。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
FlicenseAqualityFmaintenanceAn open-source server implementing the Model Context Protocol (MCP) that enables capturing insights from AI sessions and transforming them into persistent, searchable knowledge accessible across tools.78- AlicenseAqualityAmaintenanceA local-first MCP server for shared memory across AI tools, enabling context capture and resume across sessions.26624Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA lightweight, intelligent note-organizing server that acts as an AI-powered personal memory vault for capturing, organizing, and retrieving insights using FastMCP and SQLite.2
- AlicenseNot gradedqualityBmaintenanceA high-performance personal Model Context Protocol (MCP) server built with the FastMCP Python framework.MIT
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Abdullah-Zafarr/quickmemo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server