Skip to main content
Glama
Semmargl

figma-proxy-mcp

by Semmargl
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

verify_render

Compare rendered HTML against a Figma design PNG to measure visual fidelity. Returns SSIM, pixel-diff percentage, and clustered diff regions for fixing mismatches.

Instructions

Visual verification (MEASUREMENT ONLY): render an HTML file with headless Chromium INSIDE this server (does NOT use the user's Chrome / Control_Chrome) and compare it to the Figma design PNG. Returns SSIM (0-1, higher = closer), pixel-diff %, and clustered diff regions (bounding boxes of disagreement, in logical px). Provide the reference PNG via figmaUrl (auto-fetched), figmaPngPath, or figmaPngBase64. Use after generating HTML to objectively check fidelity, then fix only the reported regions — this tool never changes code. Requires npm install + npx playwright install chromium.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bgNoBackground [r,g,b] to flatten transparent reference-PNG pixels onto before comparing. Default [255,255,255]. For dark designs pass the real background (e.g. [13,17,23]) — otherwise transparent areas read as a false full diff.
clipNoOptional [x,y,w,h] in CSS/logical px to compare ONLY the content area. Use it to exclude dead margins / parent-canvas background that the isolated frame cannot reproduce (that noise otherwise dominates the regions and masks real content diffs). Region coords are reported back in full-frame coords.
scaleNoDevice scale factor for render and reference (default 2 — match render_node_png).
outDirNoDirectory for the diff image (default ./verify-out)../verify-out
figmaUrlNoFigma node URL — reference PNG fetched automatically at the given scale.
htmlPathYesAbsolute path to the generated .html file to render.
thresholdNoSSIM pass threshold (default 0.95).
frameWidthYesFigma frame width in CSS px (e.g. 1440 or 1920). HTML is rendered at this width.
figmaPngPathNoAlternative to figmaUrl: local path to an already-saved reference PNG.
figmaPngBase64NoAlternative: base64 of the reference PNG.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so richly: it declares the operation is read-only/measurement-only ('never changes code'), discloses the runtime environment (headless Chromium inside the server, not the user's Chrome), and states setup prerequisites (`npm install` + `npx playwright install chromium`). It also describes what the output contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and the MEASUREMENT ONLY qualifier, then return values, usage, and dependencies. Dense and mostly waste-free, though the single long paragraph packs many clauses and could be split for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-param tool with no output schema, the description fills the gaps: it explains the return values (SSIM, pixel-diff %, clustered diff regions in logical px), the input-source options, and the environment/setup requirements. Nothing an agent needs to call it correctly appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 10 parameters in depth. The description reinforces the reference-source choice (figmaUrl auto-fetched vs the two alternatives) but adds little semantic detail beyond what the schema provides; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (render and compare) and resource (HTML file vs Figma design PNG), and explicitly scopes it as 'MEASUREMENT ONLY'. It also disambiguates from environmental expectations by noting it 'does NOT use the user's Chrome' and runs inside the server, so an agent can distinguish it from sibling render/export tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use guidance ('Use after generating HTML to objectively check fidelity, then fix only the reported regions') and enumerates the three ways to supply the reference image (figmaUrl, figmaPngPath, figmaPngBase64). It lacks an explicit when-not/alternative-tool statement against siblings, but the context is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools