MCP server that renders AI-authored documents to images and returns typed diagnostics for self-correction. It also provides visual QA metrics, raster-to-vector reconstruction, and image-to-draft proposals.
Un-flattens flat AI designs into editable layers with bit-perfect reproduction and fidelity scoring, enabling agents to reproduce, detect elements, and diagnose designs via MCP.
Enables AI agents to automate Adobe Illustrator, converting bitmap artwork into editable .ai files, running ExtendScript, and capturing the Illustrator window for visual QA.
Enables agents to verify educational, scientific, and engineering visuals by extracting structured evidence and running domain-specific checks against specs and theory.
A multi-step academic figure agent harness that enables AI agents to plan, generate, evaluate, and iterate publication-grade figures from sources like PMIDs, preprints, or freeform briefs.
MCP server for searching, importing, and materializing scientific figure templates from FigureYa and user libraries, enabling data-driven figure selection via visual/data profiling.
