Skip to main content
Glama

Render Tool

render
Idempotent

Render Tailwind CSS or HTML to pixel-exact PNG, JPEG or WebP images in one call (Tailwind to PNG, HTML to image): social and Open Graph images, favicons and app icons, logos, banners, thumbnails and screenshots of any layout. Pass an HTML fragment styled with Tailwind v4 utility classes; there is no build step, and arbitrary values, @theme tokens and container queries work. The canvas is exactly the preset size in CSS pixels, so make the root element size-full and use portrait: and landscape: variants or vw/vh units so one design adapts across sizes, or pass overrides for a size that needs its own layout. Each image is the finished asset, not a mockup or spec sheet: never put its size, scale, aspect ratio, preset or file name in the design (no "1200 × 630" or "1:1 SQUARE" labels) unless the user asks for that text. Google Fonts load by name: list them in fonts, or just name them in --font-* tokens, font-family or font-['Instrument_Serif'] classes; css @import of a font stylesheet also works. For small images, design on a canvas of at least 200 px and set output (down to 16 px) to downscale, or pass pack: "icon" for a complete favicon and app icon set (a multi-size favicon.ico, apple-touch-icon, PWA and maskable icons, site.webmanifest and tags) from one 512x512 design. Pass brand to load a saved brand kit: colors as brand-* color tokens, fonts as font-heading and font-body, and the logo URL from get_brand. Returns permanent hosted URLs for every file, a preview_page_url to give the user (one page with the images, download buttons and X/LinkedIn/Slack/iMessage unfurl previews; it opens in any browser even when you cannot reach the file URLs), a preview image for you, and warnings listing fonts that did not load, images that failed or timed out, clipped or overflowing text and elements outside the canvas: fix those and re-render before sharing. Pass return: "inline" to also receive the image bytes yourself (sandboxes, CI, locked-down networks). The preset and pack enums list every size, so list_presets is rarely needed; call list_brands only when the user names a brand you have not seen, and get_brand before rendering with it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "markup": "<markup>"
    },
    "name": "render"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssNoExtra Tailwind CSS added after the brand @theme, for example @utility or @keyframes rules. Font stylesheet @imports are loaded as <link> tags.
packNoA set: social (og, x, linkedin, instagram, story), og, all (every social size), or icon (favicon.ico, apple-touch-icon, PWA and maskable icons, webmanifest, <head> tags).
brandNoSlug of a saved brand kit.
fontsNoGoogle Fonts families to load, for example ["Instrument Serif", "Inter"] (up to 8). Families named in markup or css load automatically; use this for fonts referenced only through a variable.
sizesNoCustom canvases in CSS pixels, 200 to 4000 per side, each with an optional output size.
markupYesHTML fragment styled with Tailwind v4 classes. Make the root element size-full. Only the design itself: no size, ratio or preset labels.
presetNoOne size: og 1200x630, x 1600x900, linkedin 1200x1200, linkedin_portrait 1080x1350, instagram 1080x1440, instagram_square 1080x1080, story 1080x1920, youtube 1280x720, icon (favicon and app icon set). Pass exactly one of preset, pack or sizes.
returnNo"urls" (default) returns hosted links; "inline" also sends each png, jpeg and webp file as image content, up to about 1 MB per call.
scalesNoPixel density per size. Default [1]; [1, 2] adds retina versions.
formatsNoOutput formats. Default ["png"]. The icon pack picks its own.
overridesNoPer-preset markup that replaces markup for that size, for example {"story": "<div ...>"}.
transparentNoTransparent background (png, webp and icons; apple-touch and maskable icons are always filled). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only supply idempotentHint, so the description carries most of the burden and does it well: it explains permanent hosted URLs, a preview_page_url usable when file URLs are unreachable, a preview image, and a warnings list of failed fonts/clipped text to fix and re-render. It also notes the ~1MB inline limit and no-build-step behavior. Minor gap: no explicit statement about rendering cost, latency, or whether old URLs expire.

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

Conciseness3/5

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

The content is high-value but delivered as one very long run-on paragraph mixing invocation mechanics, design advice, and sibling routing. It is front-loaded with purpose, but the density and lack of separation make it harder to scan than it needs to be for a 12-parameter tool.

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 complex rendering tool with no output schema, the description covers outputs (URLs, preview page, warnings, inline bytes), font loading paths, small-image downscaling strategy, and cross-size responsiveness guidance. Nothing an agent needs to call it correctly and interpret the result is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description goes beyond it by explaining the interplay of preset/pack/sizes, that overrides replace markup per size, that fonts can be loaded by naming them in --font-* tokens or font-family classes, and that brand maps to brand-* tokens and font-heading/font-body. It adds real semantic guidance rather than restating enum values.

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?

Opens with a specific verb+resource+output: renders Tailwind/HTML to pixel-exact PNG, JPEG or WebP in one call, and immediately enumerates concrete use cases (OG images, favicons, logos, banners). It also distinguishes itself from siblings by stating the preset/pack enums cover every size so list_presets is rarely needed.

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

Usage Guidelines5/5

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

Gives explicit routing rules: call list_brands only when a brand is unnamed/unseen, get_brand before rendering with it, use overrides only for sizes needing unique layouts, and choose pack over output-downscaling for favicons. When-not guidance is present (don't label images with their size/preset, don't call list_presets routinely).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources