mcpField
M
MCP Notes Server

MCP Notes Server

Remote
github.com/rwelgoshMemory & Knowledge0Updated 85w ago
Repository

About MCP Notes Server

MCP Notes Server is a small server for accessing JSON notes stored in `~/DocumentationGenerator/notes/`. It is intended for MCP clients that need to list, retrieve, or search those notes.

Key features

  1. 01List all notes
  2. 02Retrieve a note by name
  3. 03Search notes by query
  4. 04Search within a named note

Use cases

  1. 01Reviewing available notes
  2. 02Retrieving a specific note
  3. 03Finding notes that match a query
  4. 04Searching one note for relevant content

MCP support

Exposes note listing, retrieval, and search commands to MCP clients over HTTP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttp://localhost:8000
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

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:

from mcp.client import MCPClient

# Connect to the MCP server
client = MCPClient("http://localhost:8000")

# List all notes
notes = client.call("notes.list_notes")

# Get a specific note
note = client.call("notes.get_note", note_name="your-note-name")

# Search for notes
search_results = client.call("notes.search", query="important")

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.