notes-mcp-server-l16
A Model Context Protocol (MCP) server that gives Claude a persistent personal notebook. Notes are stored on disk as JSON, so they survive restarts and are shared across every tool and resource.
README
Lesson 16 — Notes MCP Server
A Model Context Protocol (MCP) server that gives Claude a persistent personal notebook. Notes are stored on disk as JSON, so they survive restarts and are shared across every tool and resource — no stubbed responses.
- Stack: Python 3.10+ · official
mcpSDK (FastMCP) · stdio transport - Theme: Notes (recommended option)
Tools
| Tool | Arguments | Required? | What it does |
|---|---|---|---|
add_note |
text: str, tags: list[str] |
text required, tags optional |
Create a note (optionally tagged) |
search_notes |
query: str |
required | Case-insensitive full-text search over text + tags |
list_notes |
tag: str |
optional | List all notes, or only those with a given tag |
delete_note |
note_id: int |
required | Delete a note by id |
(Satisfies the rubric: ≥2 tools, one with a required-only arg, one with an optional arg.)
Resources
| Resource URI | What it returns |
|---|---|
notes://all |
All notes as a JSON array |
notes://stats |
Computed stats: total count, tag frequencies, most-recent note |
note://{note_id} |
A single note by id (templated resource) |
Storage
Notes live in a JSON file, default ~/.notes_mcp/notes.json. Override with the
NOTES_DB_PATH environment variable (set in the Claude Desktop config below).
Setup
1. Install the dependency
# from this folder, using the course venv (or any Python 3.10+ env)
pip install "mcp[cli]"
2. (Optional) try it locally with the MCP Inspector
mcp dev server.py
This opens a local web inspector where you can call the tools and read the resources without Claude Desktop — handy for verifying everything works.
3. Connect to Claude Desktop
- Install Claude Desktop from https://claude.ai/download
- Open its config file (Claude Desktop → Settings → Developer → Edit Config, or
directly at
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS). - Merge in the contents of
claude_desktop_config.json. Adjust the three absolute paths to match your machine:command→ your Python interpreter (the one wheremcpis installed)args[0]→ the absolute path toserver.pyenv.NOTES_DB_PATH→ where you want the notes file
- Fully quit and reopen Claude Desktop. The
notesserver should appear under the tools (🔌 / hammer icon) in the chat input.
Example dialogs
1 — Add notes (required + optional args) 👤 Add a note "Buy oat milk and coffee beans" tagged shopping and groceries. 🤖 (calls
add_note(text="Buy oat milk and coffee beans", tags=["shopping","groceries"])) Saved note #1. Tags: shopping, groceries. 👤 Also note "Read the MCP spec" — no tags. 🤖 (callsadd_note(text="Read the MCP spec")) Saved note #2.
2 — Search & filter 👤 Which of my notes mention coffee? 🤖 (calls
search_notes(query="coffee")) 1 match for 'coffee': #1 Buy oat milk and coffee beans [tags: shopping, groceries] 👤 Show me everything tagged shopping. 🤖 (callslist_notes(tag="shopping")) … lists note #1.
3 — Resource + cleanup 👤 Give me a summary of my notebook. 🤖 (reads the
notes://statsresource) You have 2 notes; tags: shopping (1), groceries (1); most recent is "Read the MCP spec". 👤 Delete the shopping note. 🤖 (callsdelete_note(note_id=1)) Deleted note #1.
(See examples/ for real screenshots of these in Claude Desktop.)
Known limitations
- Single-user, local only. One JSON file, no auth, no multi-user support. Concurrent writes from multiple server instances could race (last-write-wins); fine for a single Claude Desktop client.
- No full-text index.
search_notesis a linear substring scan — perfectly fast for hundreds/thousands of notes, not meant for millions. - No edit/update tool. You can add, search, list, and delete; editing means delete + re-add. (Easy to extend.)
- Plain substring search, not semantic — "groceries" won't match "food" unless that word is present.
- stdio transport only. Designed to be launched by Claude Desktop; not exposed as a network service.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。