AI Sticky Notes MCP Server

An MCP server that lets an AI assistant save, read, and summarize personal notes. Notes are stored in a local notes.txt file next to the server.

Features

• add_note tool: Append a new note.
• read_notes tool: Read all saved notes.
• notes://latest resource: Retrieve the most recently added note.
• note_summary_prompt prompt: Create a prompt containing the current notes for summarization.

Requirements

• Python 3.12 or newer
• pip or uv

Run Locally

Using uv

uv sync
uv run python main.py

Using pip

Create and activate a virtual environment, then install the dependency:

python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -r requirements.txt
python main.py

The server communicates over MCP stdio, so it is normally launched by an MCP-compatible client rather than opened directly in a browser.

Test the Server

With the MCP CLI installed, start the MCP Inspector with:

mcp dev main.py

Use the Inspector to call add_note, read_notes, open the notes://latest resource, and run note_summary_prompt.

You can also verify the Python module and syntax directly:

uv run python -c "import main; print('MCP server import ok')"
uv run python -m py_compile main.py

Deploy with Smithery

The repository includes smithery.yaml, which configures Smithery to start the server with:

startCommand:
	type: stdio
	command: python
	args: ["main.py"]

Push the deployment files to a GitHub repository and deploy that repository through Smithery. The important files are:

• main.py
• requirements.txt
• smithery.yaml

notes.txt is optional because the server creates it automatically when needed. Include it only if you want to ship the sample notes.

Run with Docker

Build and start the included image:

docker build -t ai-sticky-notes .
docker run --rm -i ai-sticky-notes

Project Structure

main.py          MCP server implementation
requirements.txt Python dependencies
smithery.yaml    Smithery stdio startup configuration
Dockerfile       Container build configuration
notes.txt        Local note storage, created automatically if absent

Storage Note

Notes are stored in a plain text file. This is suitable for local use and demonstrations, but hosted containers may not preserve the file across restarts or redeployments. Durable production storage should use an external database or persistent volume.