mcpField
I
Interactive Drawing MCP

Interactive Drawing MCP

Local
github.com/AaronGoldsmithMedia & Design1Updated 83w ago
Repository

About Interactive Drawing MCP

An MCP server example that pairs a Tkinter drawing window with tools for controlling a 16×16 grid. It is intended for interactive drawing with Goose or other MCP clients, with grid state saved between sessions.

Key features

  1. 01Interactive 16×16 drawing grid
  2. 02Start a drawing session
  3. 03Toggle individual cells
  4. 04Read grid state as text
  5. 05Persist state in JSON

Use cases

  1. 01Draw patterns through tool calls
  2. 02View the current grid state
  3. 03Continue with saved drawing state

MCP support

Exposes tools to start a session, toggle grid cells, and retrieve the grid state. The server connects Goose AI tool calls to the Tkinter interface.

#tkinter-canvas#mcp-server#python-mcp

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

Interactive Drawing MCP

This project is an example of a Model Context Protocol (MCP) server with an interactive drawing interface. It demonstrates how to build an MCP extension that includes a separate UI window for drawing, using Tkinter as the graphical interface.

Features

  • Drawing Grid Interface:

    • Offers a 16x16 grid where each cell can be toggled between two states (filled or empty).
    • Provides a clear grid button to reset all cells.

  • Server Capabilities:

    • Start Drawing Session: Initializes a new session and launches the UI.
    • Toggle Cell: Toggle the color of individual cells via a command interface.
    • Get Grid State: Retrieve the current grid configuration as a text representation.

  • Persistence: Grid state is saved to a JSON file (board_state.json) to maintain consistency across sessions.

  • UI and State Synchronization:

    • Real-Time UI Update: A background thread continuously watches for updates to the grid state file and reflects changes visually.

Installation

Option 1: Install from Source

  1. Clone this repository:

    git clone https://github.com/AaronGoldsmith/interactive_draw_mcp
cd interactive_draw_mcp

  2. Install the package:

    pip install -e .

Usage

As a Standalone MCP Server

Run the server to open the drawing window:

interactive-draw-mcp
With Goose
Option 1: Using Goose CLI (recommended)

Start Goose with your extension enabled:

# Local Development
goose session --with-extension "python -m interactive-draw-mcp"

Tools

  • Server Tools:
    • start_drawing_session(): Initializes a drawing session and opens the UI.
    • toggle_cell_color(row, col): Toggles the cell's color at specified row and col.
    • get_grid_state(): Provides a string representation of the grid's current state.
Resources and References

Architecture Overview

The architecture of this project demonstrates:

  1. MCP Server: Manages communication between the Goose AI and the drawing interface via well-defined tools.
  2. Interactive UI: Provides a visual interface for the grid.
  3. Integration with Goose AI: Tool calls from Goose AI reflect directly onto the grid state and vice versa.
Benefits
  • Separation of Responsibilities: Maintains clear separation between server logic and UI presentation.
  • Improved User Experience: Offers intuitive visual feedback alongside text-based command interface.
  • Adaptability: Can be extended to more sophisticated applications involving AI and interactive UIs.

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.