mcpField
N
NoteFlow-MCP

NoteFlow-MCP

Remote
github.com/Surendhar-23Productivity0Updated 33w ago
Repository

About NoteFlow-MCP

NoteFlow-MCP is a FastMCP v2 server that connects to a notes-style API. It exposes note creation and listing; the included DummyJSON backend simulates writes rather than persisting them.

Key features

  1. 01Create notes with a title and content
  2. 02List notes from the API
  3. 03Configure a notes API backend

Use cases

  1. 01Create notes through an MCP client
  2. 02List notes available from the configured API

MCP support

It exposes `create_note` and `list_notes` tools to MCP clients.

Configuration

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

Endpointhttps://2c08-27-4-120-4.ngrok-free.app/mcp
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

noteflow-mcp

noteflow-mcp is a FastMCP v2 server that connects to a notes-style API.

Setup

Install dependencies:

uv sync

Create your environment file:

cp .env.example .env

Then update .env with your real notes API settings.

The current default uses DummyJSON's free posts API as a notes backend:

  • GET https://dummyjson.com/posts
  • POST https://dummyjson.com/posts/add

DummyJSON does not require an API key, so NOTES_API_KEY can stay empty.

Run locally

uv run noteflow-mcp

Or:

uv run python -m noteflow_mcp.server

Exposed tools

  • create_note(title, content)
  • list_notes()

create_note maps note content to DummyJSON's body field. DummyJSON simulates writes for testing, so created notes are not persisted server-side.

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.