mcpField
N
notes-mcp-server

notes-mcp-server

Local
github.com/coilybitsMemory & Knowledge0Updated 79w ago
Repository

About notes-mcp-server

notes-mcp-server is an MCP server for AI assistants to manage structured notes, persisted with Apache Ignite. It exposes note operations alongside prompts.

Key features

  1. 01List database notes
  2. 02Read notes
  3. 03Create and delete notes
  4. 04List and view prompts

Use cases

  1. 01Find saved notes
  2. 02Create or remove notes
  3. 03Use prompts to assist note operations

MCP support

The MCP server exposes note listing and reading as resources, create and delete operations as tools, and prompt access to clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "notes": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/inspector

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/inspector

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

notes-mcp-server

A Model Context Protocol (MCP) server which provides AI assistants with a secure and structured way to CRUD simple notes. The notes are persisted using apach ignite

Capabilities

  • list_resources list all notes in database
  • read_resource reads a note from database
  • list_tools list tools AI assistants can access
  • call_tool executes a tool (create note, remove note)
  • list_prompts list of helpful prompts
  • get_prompt view prompt

Configuration

  • --host the database host
  • --port the database port

Usage

Continue.dev

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "/path/to/uv",
          "args": [
            "--directory",
            "/path/to/notes-mcp-server",
            "run",
            "main.py"
          ]
        }
      }
    ]
  }
}

Claude Desktop

Configure the MCP server in Claude configuration file:

{
  "mcpServers": {
    "messaging": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/path/to/notes-mcp-server",
        "run",
        "main.py", "--host=127.0.0.1", "--port=10800"
      ]
    }
  }
}

License

MIT License - see LICENSE.

Prerequisites

  • Python with uv package manager
  • MCP server dependencies
  • Apache Ignite

Development

# Clone the repository
git clone https://github.com/coilybits/notes-mcp-server.git
cd notes-mcp-server

# Create virtual environment
uv venv
source venv/bin/activate 

# Install development dependencies
uv sync

MCP Inspector for debugging:

npx @modelcontextprotocol/inspector uv \
--directory \
/path/to/notes-mcp-server \
run \
main.py

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.