Visionaire Engine
未认领Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line — and why. Cascade verdicts, blast radius, interaction timelines, pixel-perfect audits.
安装
claude mcp add visionaire -- npx -y visionaire-engine更多Files & Storage服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
25 个工具中显示 25 个
文档中列出的工具 (25)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
annotated_screenshot
Screenshot with numbered marks that equal snapshot uids — or an element-scoped crop via clipTo with padding/scale zoom and optional annotate:false
assert_visual
The verification gate. State rendered-geometry claims (equal heights, alignment, gaps, clipping, colors, z-order — 17 assertion types) → deterministic PASS/FAIL with measured pixels and offending uids; register named suites and re-run them after every edit
capture_proof
Before/after evidence bundles: annotated screenshots + suite verdicts, with a verdict delta proving the fix flipped FAIL → PASS
check_alignment
(deprecated → assertvisual) Group pixel audit: which of N elements is off-alignment by how many px, gap-rhythm outliers, size consistency, N-px grid conformance, pixel-snap warnings
diagnose
One-shot "why does this look broken" — ranked culprits with measured evidence for clipping, overflow, off-center, invisibility, overlap, wrong size
evaluate
Escape hatch: run agent-authored JavaScript in the page and get the JSON result, for the genuinely bespoke case no other tool covers
explain_animations
Animations/transitions touching an element: live census, declared rules with file:line, and a closed "why is it not smooth" ruleset
explain_styles
The wedge. Cascade winner/loser per property with file:line + origin attribution, each winner's blast radius (how many other elements it styles), and a scoped-fix selector for just this element
find_elements
Deterministic search by text, selector, role, or screen region — AND-combined by default, match:"any" for a union, visibleOnly:false to include hidden elements
get_listeners
Event listeners on an element + its ancestors, with handler file:line and capture/passive/once flags
impact_preview
Blast-radius report before editing a shared selector: who else matches, grouped with uids, plus a sandboxed dry-run predicting exactly which elements would change
inject_css
The live fix loop: trial declarations on an element (or a page-wide rule) without touching source — see what changed, converge, write source once, revert
inspect_ancestors
Constraint-chain walk: which ancestor constrains width/overflow/stacking
inspect_element
The "what": box model, computed values, visibility verdict
interact
Drive the UI into a state (open a menu/popup/modal, reveal a tab) and leave it there so you can inspect the new state — reports post-action visibility + box
measure_element
Sub-pixel rendered geometry: content box + true text-ink box (glyph extents) with a centering verdict — "is this × actually centered?"
node_at_point
x,y → element uid + ancestor chain
page_origins
Stylesheet inventory + platform detection (WordPress version, theme, builders, optimizers)
page_snapshot
Pruned, uid-keyed tree of what's visible — geometry, layout hints, invisibility reasons
pick_color
The actual painted pixel (composited truth: gradients, images, opacity) + computed colors + WCAG AA/AAA contrast verdict
pick_element
Human-in-the-loop grounding: DevTools-style hover highlight, the user clicks the element that looks wrong
record_interaction
One interaction → a source-attributed causal timeline: handlers, mutations, cancelled transitions, layout shifts
responsive_sweep
One verification payload across many viewports → a per-viewport verdict matrix ("fixed on desktop, still broken on mobile" caught in one call)
style_diff
Record styles, compare later — verify-my-fix loops
visual_diff
Pixel-diff the live page (or one element) against a mockup PNG or a recorded baseline — MATCH/DIVERGENT with divergent regions mapped back to element uids, optional heatmap artifact