mcp-painter
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| drawing_generateCanvasC | Generate a new drawing canvas with specified width and height. |
| drawing_fillRectangleC | Fill a rectangle on the drawing canvas with a specified color and coordinates. |
| drawing_getCanvasPngA | Get the current drawing canvas as a PNG image (base64 encoded). |
| drawing_getCanvasDataB | Get the current pixel data of the drawing canvas as JSON. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Current Canvas as PNG Image | |
| Current Canvas Data (JSON) |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: generating a canvas, filling a rectangle, retrieving canvas data as JSON, and retrieving canvas data as PNG. There is no overlap in functionality, making it easy for an agent to select the correct tool for each operation.
All tools follow a consistent 'drawing_verbNoun' pattern (e.g., drawing_generateCanvas, drawing_fillRectangle). This predictability enhances usability and reduces confusion, as the naming convention is uniform across all tools.
With 4 tools, the server is well-scoped for basic drawing operations, covering canvas creation, drawing, and data retrieval. However, it lacks advanced features like drawing other shapes or clearing the canvas, which might be expected in a drawing domain, making it slightly under-equipped but reasonable.
The tools cover core operations for a drawing server: create canvas, draw (fill rectangle), and retrieve data. However, there are notable gaps, such as no tools for drawing other shapes (e.g., circles, lines), clearing the canvas, or updating existing drawings, which limits the agent's ability to perform more complex tasks.