$ loading_
Create, render, and validate 3D scenes, 2D art, and canvas games.
This MCP tool is described as a local utility for creating and rendering 3D/2D scenes, taking screenshots, validating output, and playtesting; the materials do not indicate any required secrets or remote endpoints, so it appears primarily local. The main concerns are its inherent local code-execution capability and the weaker supply-chain signals from a third-party registry entry with low adoption and unclear maintenance, so source review is advisable before use.
The materials explicitly state that no keys or environment variables are required, and no API tokens, account credentials, or external service authorizations are mentioned; based on the available information, credential exposure and misuse risk appears low.
The materials explicitly list no remote endpoints, and the description focuses on local HTML canvas/Three.js/WebGL rendering, screenshots, and validation, with no evidence that user data is sent to external services.
The system checks confirm it has code-execution capability; combined with its scene creation, rendering, screenshot, and playtesting functions, it is reasonable to infer that it starts local rendering or related execution workflows. This is a common MCP/tool capability, and the current materials do not show requests for system privileges beyond its stated purpose, but it should still be treated as a local execution tool and isolated accordingly.
Its functionality involves generating 3D/2D content and producing screenshots and validation reports, which typically implies reading and writing local project files or artifacts; however, the materials do not specify directory scope or whether it can recursively access arbitrary paths, so the data-access boundary is not clearly defined.
A public GitHub repository is available for audit, which is a positive factor that lowers risk; however, the source is a third-party registry, the license is unspecified, community adoption is only 0 stars, and maintenance status is unknown, so trust and maturity signals are relatively weak. Review the repository contents and dependencies before use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "canvas3d-mcp" yet — see the docs or source repo.
Use Three.js in an HTML canvas to create a rotatable 3D product showcase scene: a smartwatch in the center, with soft lighting, floor reflections, and a light background. Render the scene and return multi-angle screenshots plus a scene structure summary.
An interactive 3D showcase scene, screenshots from multiple angles, and a summary of scene objects and render settings.
Create a simple web mini-game using Canvas 2D or WebGL: the player controls a character to avoid falling obstacles, with start, scoring, and restart-on-failure logic. Then run interactive playtesting and provide a validation report covering collisions, performance, and input responsiveness.
A mini-game prototype, playtest results, and a structured validation report on functionality and performance issues.
Draw a 2D sci-fi city night illustration in an HTML canvas, including neon lights, flying cars, and distant skyscrapers. After rendering, inspect composition, layer relationships, element completeness, and visual consistency, then return validation findings and preview screenshots.
The rendered illustration, preview screenshots, and an inspection report on visual structure and completeness.
Access Canvas LMS data and safely perform course-related actions via API.
Connect to Canvas LMS to manage courses, assignments, grades, and teaching tasks.
Generate videos, images, audio, and 3D models through MCP-compatible AI agents.
Manage Canvas courses, assignments, grades, and admin tasks with natural language.
Let AI read and write local infinite canvas data with visualization.
Generate PBR-textured 3D models from text or images with MCP integration.