Clip.A.Canvas renders HTML/CSS/JS animations into MP4 videos using Chromium and FFmpeg, either locally or via a hosted cloud endpoint. Its MCP server exposes video-rendering tools to AI clients, and the project also includes a desktop app and terminal UI for local use.
From the registry: Render HTML, CSS, SVG, and Canvas animations to MP4 locally via Playwright/Chromium and FFmpeg.

$ uv --versionhttps://docs.astral.sh/uv/Please install the `clipacanvas` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install uvx or Python packaging tooling — To run the local MCP server via the recommended portable path, install uv (which provides uvx). As an alternative, you can install the package with pip. Run: `uv --version` (https://docs.astral.sh/uv/)
- Optional cloud-hosted endpoint available — Instead of running locally, you can connect directly to the hosted SSE MCP server. (https://mechreaper007x-clip-a-canvas-mcp.hf.space/sse)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","clipacanvas-mcp","clipmcp"]
Note: README provides two MCP connection modes: local stdio via uvx/pip package, and a hosted SSE endpoint at https://mechreaper007x-clip-a-canvas-mcp.hf.space/sse. Per the simplest portable local path rule, the canonical config uses the stdio uvx command. No environment variables are documented for the MCP server.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Make 3D games in Unity Engine with AI. MCP Server + Plugin for Unity Editor and Unity games.