NotePilot
A Python MCP server that exposes note management tools (create, search, update, delete notes) over stdio, enabling Claude AI to manage notes through natural language conversation.
README
NotePilot (Notes Assistant AI Chat App)
Turn thoughts into structured knowledge..!
A minimal Notes application built on the Model-Context-Protocol (MCP). A Python MCP server exposes note management tools over stdio; an async client connects Claude AI to those tools so you can create, search, and manage notes through a natural-language chat interface.
Overview
You ──► Claude AI (Anthropic) ──► MCP Client ──► MCP Server ──► SQLite
(tool calls) (stdio) (FastMCP) (notes.db)
Claude receives a set of note-management tools from the MCP server. When you ask it to "create a note about X" or "find notes mentioning Y", it invokes the appropriate tool, gets the result, and responds conversationally.
Tech Stack
| Layer | Technology |
|---|---|
| Language | Python 3.12+ |
| Package manager | uv |
| MCP framework | mcp[cli] (FastMCP) |
| AI / LLM | Anthropic SDK (AsyncAnthropic) |
| Database | SQLite via sqlite-utils |
| CLI formatting | colorama |
| Config | python-dotenv |
Prerequisites
- Python 3.12+
- uv installed
- An Anthropic API key
Configuration
Create a .env file in the project root:
ANTHROPIC_API_KEY="sk-ant-..."
CLAUDE_MODEL="claude-haiku-4-5-20251001"
Installation
# Clone the repo
git clone https://github.com/chaitanya-jadhav11/notes-mcp
cd notes-mcp
# Install dependencies
uv sync
Usage
# Start the interactive chat client
uv run -m client.client
You can then chat naturally with Claude. Examples:
You: Create a note titled "Shopping list" with milk, eggs, and bread.
You: Show me all my notes.
You: Search for notes about bread.
You: Update the shopping list to add butter.
You: Delete the shopping list note.
To inspect or develop the MCP server interactively:
uv run mcp dev server/server.py
Project Structure
notes-mcp/
├── .env # API key and model config (create this)
├── pyproject.toml # Project metadata and dependencies
├── uv.lock # Pinned dependency lock file
├── notes.db # SQLite database (auto-created on first run)
│
├── server/
│ ├── server.py # FastMCP server — defines the 8 note tools
│ └── db.py # SQLite CRUD layer (UUID keys, ISO timestamps)
│
└── client/
├── client.py # MCPClient class + interactive REPL loop
└── claude_client.py # Anthropic API wrapper — manages conversation
# history, tool-call loops, and prompt caching
Available MCP Tools
The server exposes the following tools to Claude:
| Tool | Description |
|---|---|
list_notes |
List all notes (id + title) |
create_note |
Create a note with a title and body |
get_note_by_id |
Fetch a single note by UUID |
get_notes_by_title |
Find notes by exact or partial title match |
search_notes |
Full-text search across note bodies |
update_note |
Update a note's title and/or body |
delete_note_by_id |
Delete a note by UUID |
delete_notes_by_title |
Delete all notes matching a title |
App Screenshot

Anthropic course certificate

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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。