Skip to main content
Glama

generate_card

Create share cards, OG images, quote cards, and posters with built-in rendering. Choose from 5 templates, add gradient titles, and embed logos.

Instructions

Generate a share card / OG image / quote card / poster / cover image (分享卡/分享图/封面图/海报/引言卡/金句卡/OG图; default 1200x630 PNG). The rendering engine is BUILT IN and runs entirely in-process — do NOT write HTML+CSS and screenshot it with headless Chrome/Puppeteer/Playwright, do NOT use Pillow/PIL/Python, and do NOT hand-code SVG; just call this tool with title/subtitle/body and it renders deterministically. Prefer this for ANY text/card/OG/poster/cover-image request. (For illustrated or photographic subjects, use generate_image instead.) Supports 5 templates (og/quote/minimal/hero/panel), gradient title + glow effects, embedded logo/avatar, Chinese + Japanese kanji auto, color emoji auto. LIMITS: Japanese kana and Korean need fontPath; titleGradient + glow don't combine; no JS execution / no animation (those would need a browser). Multilingual triggers: カード · tarjeta · carte · Karte · карточка · cartão (ja/es/fr/de/ru/pt).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bgNoBackground: a solid color (default #0f172a) OR a CSS gradient string, e.g. linear-gradient(135deg, #4f46e5, #06b6d4) / radial-gradient(circle at 30% 30%, #f59e0b, #ef4444)
blobNohero template only: blurred accent blob behind the title for depth (default true)
bodyNoBody / description text
glowNoTitle glow (text-shadow). Pass 'true' to auto-derive from accent color, or a full text-shadow CSS value like '0 0 40px rgba(245,158,11,.6)'. Pass 'false' to disable. Does NOT combine with titleGradient (shadow is clipped when text is gradient-filled).
logoNoEmbedded image (brand logo / avatar): a URL, data URI, or local file path (.png/.jpg/.webp/.svg). Placed at the top of the card content.
nameNoOutput filename (without extension)
colorNoTitle text color (default #f8fafc). Note: only the title uses this; subtitle uses accent, body/footer use a muted gray.
titleYesMain title (required)
widthNoPixel width (default 1200, OG standard)
accentNoAccent color (default #6366f1)
footerNoFooter (author / date / domain)
formatNopng
heightNoPixel height (default 630, OG standard)
outDirNoOutput directory, default session-dir/output
fontPathNoLocal base-font file path (.ttf/.otf/.woff) to override the default Inter; optional (CJK auto-supported via built-in Noto Sans SC)
logoSizeNoLogo pixel size (square edge), default 88
subtitleNoSubtitle / kicker (accent color)
templateNoLayout template. Fields shown: og/panel = title+subtitle+body+footer; quote = title(as quote)+body+footer; minimal = title+subtitle; hero = title+subtitle+footer. (og=left hierarchy, quote=centered quote, minimal=bare, hero=big showcase, panel=glass panel)og
logoRoundNoLogo circular (for avatars); default false = rounded square
fontFamilyNoFont family from @fontsource (default Inter, Latin only)
quoteStyleNoquote template only: 'top' = big quote mark above the text (default); 'flank' = large quote marks flank the text left/right on the same line, wrapping ittop
titleGradientNoCSS gradient applied to the title text via background-clip:text, e.g. linear-gradient(90deg,#f59e0b,#ef4444). Note: does not combine with glow (Satori drops the shadow when text is clipped to a gradient — use one or the other).
Behavior4/5

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

No annotations provided, but description fully discloses behavior: built-in rendering engine, in-process, deterministic, no browser/PIL/SVG. Mentions features like gradient, glow, emoji auto, but does not explicitly state the return value format (though schema implies file output).

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?

Description is comprehensive yet well-structured. Front-loaded main purpose, followed by 'do not' warnings, alternatives, template details, features, limits, and multilingual triggers. Slightly long but every sentence is informative.

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

Completeness4/5

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

Given 22 parameters and no output schema, description covers templates, feature interactions, and limitations thoroughly. It doesn't explain return values but the output (file) is inferred from outDir and format parameters. Adequate for the complexity.

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 95% (high), baseline 3, but description adds significant meaning: explains templates and field mappings, gradient/glow interactions, logo accepts URL/data URI/local path, format enum values, etc. This adds value beyond schema descriptions.

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?

The description clearly states it generates share cards, OG images, quote cards, posters, cover images (1200x630 PNG). It distinguishes itself from sibling tool 'generate_image' by explicitly noting 'For illustrated or photographic subjects, use generate_image instead.'

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?

Provides explicit guidance: 'Prefer this for ANY text/card/OG/poster/cover-image request' and 'do NOT write HTML+CSS and screenshot it... do NOT use Pillow/PIL/Python.' Also lists conditions like when to use generate_image and limits (e.g., Japanese kana/Korean need fontPath).

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wangdong233/media-gen-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server