Cavi Adobe Authoring MCP
Related Servers
Alternatives to Cavi Adobe Authoring MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to automate and inspect Adobe Photoshop, Premiere Pro, After Effects, and Illustrator through a secure, typed MCP surface with schema-validated operations, risk-classified plans, artifacts, and verification. Bridges translate safe domain commands into UXP, CEP, ExtendScript, or approved CLI work without exposing arbitrary scripts or shell access.MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to perform validated, authenticated project, timeline, media, marker, and export-queue operations in Adobe's video editor through a local UXP panel. It supports safe previews and explicit approval for destructive actions.6,095 npmMIT
- AlicenseBqualityBmaintenanceEnables any MCP client to control After Effects, Premiere Pro, Photoshop and Illustrator through 182 native tools plus 500+ bundled community tools, covering layer/comp editing, rendering, export, plugin and extension discovery, and media downloads. Cross-app workflows move comps, layers, frames and MOGRTs between applications, while raw scripting escape hatches reach nearly any menu command or plugin action.1821MIT
- AlicenseAqualityBmaintenanceEnables local control of Adobe After Effects via MCP, offering offline creative skills, project inspection, and operation execution without cloud relay or an installed AE panel.122,219 npm13MIT
- AlicenseAqualityBmaintenanceEnables MCP clients to safely read, write, edit, search, and optionally run commands within one or more named project workspaces, while maintaining a work journal and tracking changes.19MIT
- FlicenseNot gradedqualityBmaintenanceEnables local publication cataloguing, persistent native DesignCraft editing sessions, page workspace operations, source linking via hoard:// references, preview rendering, and verified multipage RGB-raster PDF export through MCP tools.-
TDQS
Scored across 17 tools
Most tools target a distinct resource+action (open_copy, create_canvas, place_image, add_text, apply_mask, export, close_copy), so an agent can generally select correctly. The main soft spots are the state-inspection cluster (adobe_status vs adobe_inspect vs adobe_operation_control) and the two geometry creators (adobe_add_rectangle vs adobe_add_path), which require reading descriptions to separate.
The majority are snake_case verb_noun with an adobe_ prefix, but the prefix scheme is split (adobe_*, after_effects_render, media_review_movie) and two tools (adobe_fonts, adobe_operation_control) are noun-only rather than verb-led. Still readable, but not a single predictable convention.
17 tools is at the heavy edge for a single server, but the scope genuinely spans Photoshop, Illustrator, After Effects rendering, and FFmpeg review, and each tool maps to a distinct authoring step. Nothing looks like filler, though it is close to the point where splitting by app would help.
The lifecycle is well covered: open/copy, canvas creation, composition primitives (group, image, rect, path, text), layer edit, masking, export, close, and retained-operation recovery, plus render and review for animation. The notable gap is mutation of existing content — no delete/remove, move/transform, or text re-edit tool — so revisions rely on rebuilding or discarding the owned copy.