sticky-notes
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@sticky-notes add a note to buy coffee beans"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-server-demo
A minimal Model Context Protocol server that gives an LLM a persistent scratchpad. It exists to demonstrate all three MCP primitives — tools, resources, and prompts — in about 80 lines of Python.
Built against the Python SDK v2 (mcp>=2.1.1), where FastMCP was renamed to MCPServer.
What it exposes
Primitive | Name | Purpose |
Tool |
| Appends a note. Model-invoked. |
Tool |
| Returns every stored note. |
Resource |
| The most recent note, as read-only context. |
Prompt |
| A reusable prompt that pulls the notes in and asks for a summary. |
The tool/resource split is the point worth noticing. read_notes is a tool because the model decides when to call it. notes://latest is a resource because the client decides when to attach it — it's context, not an action.
Related MCP server: flomo-mcp
Install
Requires Python 3.12+ and uv.
git clone https://github.com/DinaMMahfouz/mcp-server-demo.git
cd mcp-server-demo
uv syncVerify it imports cleanly:
uv run python -c "import mcp_server_demo.main; print('ok')"Run
uv run mcp-server-demoThe process will appear to hang. That is correct — it speaks JSON-RPC over stdio and is waiting for a client. Ctrl+C to exit.
To poke at it interactively:
uv run mcp dev src/mcp_server_demo/main.pyConnect to Claude Desktop
Edit claude_desktop_config.json:
Windows —
%APPDATA%\Claude\claude_desktop_config.jsonmacOS —
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"sticky-notes": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-server-demo",
"run",
"mcp-server-demo"
]
}
}
}The path must be absolute. Restart Claude Desktop; the tools appear in the tools menu.
Storage
Notes are written to a per-user data directory, not into the package:
Windows —
%LOCALAPPDATA%\mcp-server-demo\notes.txtLinux/macOS —
$XDG_DATA_HOME/mcp-server-demo/notes.txt, falling back to~/.local/share/
Override with the STICKY_NOTES_FILE environment variable.
Scope
This is a learning project. It has no tests, no concurrency handling, and no input validation beyond stripping whitespace — a plain-text file appended to by one process. Don't build on it.
License
MIT.
Available Tools
2 toolsadd_noteA
Append a note to the notes file.
Parameters
----------
message : str
The note to append.
Returns
-------
str
Confirmation that the note was stored.
Inputs: message (required). Returns: result
read_notesA
Read every stored note.
Returns ------- str All notes, newest last, or a message saying there are none.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one reads all notes and the other appends a note. There is no overlap or ambiguity between them.
Both tools follow the same lowercase verb_noun pattern: read_notes and add_note. The naming is simple, predictable, and consistent.
With only two tools, the server feels minimal but not unreasonable for a basic sticky-notes utility. However, it is on the thin side and offers little beyond append and read-all functionality.
The server supports creating and reading notes, but lacks update and delete operations, which are common expectations for a note-taking tool. Agents can work around this limitation only if no note modifications or removals are required.
Maintenance
Related MCP Connectors
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Cross-tool persistent memory and context for AI assistants over MCP.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceA simple notes system that allows creating, storing, and accessing text notes through MCP resources and tools, with built-in prompt support for generating summaries of stored notes.-
- FlicenseBqualityDmaintenanceEnables writing and managing notes to flomo via MCP. Provides tools for creating notes, resources for accessing them, and prompts for summarization.124 npm-
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to manage in-memory notes by listing, fetching, and creating notes through MCP tools over stdio.118 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables LLM clients to read, search, create, update, and delete notes in a self-hosted shared memory bank over MCP, using hybrid vector and full-text search with optional summarization.4MIT