Enables LLM agents to programmatically inspect hardware resources, run in-memory inference benchmarks, list supported fMRI studies, and retrieve cortical and subcortical atlas region indices via JSON-RPC 2.0.
Provides an MCP server that lets AI models build and patch typed SVG scenes, compute exact Bézier geometry, perceptual gradients and keyframe or spring motion, then rasterize the result to PNG or animated APNG and diff renders pixel-by-pixel. Ten math-backed tools replace guessed coordinates with deterministic geometry, color and animation output.