Non Dirty MCP Client And Server

A client and server project implementing the MCP protocol, providing note storage, summary generation, and note - adding functions

Note-taking tools Knowledge management and memory #Note Management #Protocol Service #Summary Generation .Python

rating : 2 points

downloads : 14

update time : 2025-04-29

What is an MCP server?

An MCP server is a tool that supports the model context protocol, allowing users to store, manage, and generate note summaries. It accesses individual notes through a custom note:// URI scheme and provides a summary generation function.

How to use an MCP server?

Users can use the server by adding notes, setting styles, and generating summaries. The server automatically updates note status and sends change notifications to clients.

Applicable scenarios

Suitable for individuals or teams that need to efficiently manage notes and generate summaries, such as students, researchers, and enterprise users.

Main Features

Note Storage SystemSupports accessing and managing notes through a custom note:// URI scheme.

Generate SummariesGenerates summaries of all notes according to the user - selected style (brief/detailed).

Add New NotesSupports adding new notes via the command line and instantly synchronizing them to the server.

Advantages and Limitations

Advantages

A simple and easy - to - use command - line interface

Supports summary generation in multiple styles

Real - time update and notification mechanism

Limitations

Relies on command - line operations

Has certain requirements for the network environment

How to Use

Install the MCP Server

Download and install the MCP server as instructed in the documentation.

Start the Server

Run the start command in the terminal to initialize the server.

Add a Note

Use the add - note command to add a new note.

Generate a Summary

Call the summarize - notes command to generate a note summary.

Usage Examples

Add a NoteAdd a new note to the server.

Generate a SummaryGenerate a detailed summary of all notes.

Frequently Asked Questions

How to install the MCP server?

How to generate a note summary?

Does the server support real - time updates?

Related Resources

MCP Server Documentation

Comprehensively understand detailed information about the MCP server.

GitHub Code Repository

View source code and contribute.

MCP Inspector

A tool for debugging and monitoring the MCP server.

🚀 MCP Client and Server

The Model Context Protocol client and server are used to chain-connect clients and servers.

🚀 Quick Start

📦 Installation

On MacOS:

~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Development/Unreleased Server Configuration

``` "mcpServers": { "mcp-client-and-server": { "command": "uv", "args": [ "--directory", "/Users/mlrsmith/Library/Mobile Documents/com~apple~CloudDocs/Family_Shared/AI/mcp/mcp-client-and-server", "run", "mcp-client-and-server" ] } } ```

Released Server Configuration

``` "mcpServers": { "mcp-client-and-server": { "command": "uvx", "args": [ "mcp-client-and-server" ] } } ```

✨ Features

Resources

The server implements a simple note storage system with the following features:

A custom note:// URI scheme for accessing individual notes.
Each note resource has a name, description, and text/plain MIME type.

Prompts

The server provides a prompt:

summarize-notes: Generate a summary of all stored notes.
- An optional "style" parameter to control the level of detail (concise/detailed).
- Generate a prompt containing the content of all current notes based on style preferences.

Tools

The server implements a tool:

add-note: Add a new note to the server.
- Accept "name" and "content" as required string parameters.
- Update the server state and notify the client of resource changes.

🛠️ Development

Build and Publish

To prepare a distribution package:

Synchronize dependencies and update the lock file:

uv sync

Build the package release version:

uv build

This will create source code and wheel distributions in the dist/ directory.

Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command-line parameters:

Token: --token or UV_PUBLISH_TOKEN
Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs via standard input and output, debugging can be difficult. For the best debugging experience, we highly recommend using the MCP Inspector.

You can start the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory /Users/mlrsmith/Library/Mobile Documents/com~apple~CloudDocs/Family_Shared/AI/mcp/mcp-client-and-server run mcp-client-and-server

After starting, the inspector will display a URL in the browser where you can start debugging.