MCP Notes Server

by rwelgosh

170 downloads
Not rated
GitHub

Description

# MCP Notes Server A simple MCP (Message Coordination Protocol) server that provides access to notes stored in `~/DocumentationGenerator/notes/`. ## Setup 1. Make sure you have Python 3.7+ installed 2. Create a virtual environment: ``` python -m venv venv ``` 3. Activate the…

About

# MCP Notes Server A simple MCP (Message Coordination Protocol) server that provides access to notes stored in `~/DocumentationGenerator/notes/`. ## Setup 1. Make sure you have Python 3.7+ installed 2. Create a virtual environment: ``` python -m venv venv ``` 3. Activate the virtual environment: - On macOS/Linux…

Details

Author
rwelgosh
Downloads
170
Categories
Knowledge Base

- Exposes notes via MCP over HTTP on port 8000.
- Supports three commands: list, get, and search notes.
- Notes are stored as JSON files with category, tags, and messages.
- Each message includes a timestamp and content.
- Simple Python setup with a virtual environment and requirements file.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Notes Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

To use it, set up a Python virtual environment (Python 3.7+), install dependencies with pip install -r requirements.txt, then start the server by running python notes.py. The server listens on http://0.0.0.0:8000. Clients connect via MCP client libraries and call commands such as list_notes(), get_note(note_name), and search(query, note_name=None).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp notes server": {
            "mcp-notes-server": {
                "type": "http",
                "url": "http://localhost:8000"
            }
        }
    }
}

McpServers

{
    "mcp-notes-server": {
        "type": "http",
        "url": "http://localhost:8000"
    }
}

MCP Notes Server

A simple MCP (Message Coordination Protocol) server that provides access to notes stored in ~/DocumentationGenerator/notes/.

Setup

1. Make sure you have Python 3.7+ installed
2. Create a virtual environment:

   python -m venv venv

3. Activate the virtual environment:
- On macOS/Linux: source venv/bin/activate
- On Windows: venv\Scripts\activate
4. Install dependencies:
   pip install -r requirements.txt

Running the Server

To start the MCP server:

python notes.py

This will start the server on http://0.0.0.0:8000.

API Endpoints

The server exposes the following MCP commands:

- list_notes() - Get all notes
- get_note(note_name) - Get a specific note by name
- search(query, note_name=None) - Search notes by query string

Note Format

Notes are stored as JSON files in the specified directory with the following format:

{
    "category": "category",
    "summary": "summary of the notes", 
    "tags": [
        {
            "tag": "tag of the sub detail",
            "summary": "high level business logic of the sub details",
            "messages": [
                {
                    "timestamp": "timestamp of the message",
                    "message": "message content"
                },
                {
                    "timestamp": "timestamp of the message",
                    "message": "message content"
                },
                ...
            ]
        }
    ]
}

Client Usage Example

Here's a simple Python example of how to connect to the MCP server from a client:

```python
from mcp.client import MCPClient

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.