A1 Gallery MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@A1 Gallery MCP ServerFind three brutalist law firm sites and show me their heroes."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A1 is a hand-picked gallery of real website designs. This MCP server puts it inside your coding agent, so you can ask for a reference and get structured JSON back instead of pasting screenshots and describing what you want.
Every site is captured at full length, split into its interior pages and its individual sections, then measured. You get the type sizes, spacing, radius, container width and palette taken off the rendered page — not guessed from a picture.
In the gallery right now: 1,165 sites · 3,209 captured sections · 2,860 full-page captures · 571 fonts · 517 designers and studios.
Endpoint
URL |
|
Transport | Streamable HTTP |
Auth | OAuth 2.1 with PKCE, dynamic client registration |
Registry name |
|
Tools | 17, all read-only |
Access is free with an A1 account — 50 tool calls a day. A1 Pro raises that to 2,000 a day with a higher per-minute allowance.
Related MCP server: AllGoodInsp
Install
Your client opens a browser to sign in the first time it connects. Per-client instructions with one-click install links are at a1.gallery/mcp.
Claude Code — plugin
The plugin in this repository bundles the server with three skills, three slash commands and a research sub-agent. It teaches the agent how to use the gallery, which the bare connector does not.
claude plugin marketplace add bryntay/a1-mcp
claude plugin install a1-galleryThen run /mcp and authenticate. See Plugin below for what it adds.
Claude Code — connector only
claude mcp add --transport http a1 --scope user https://www.a1.gallery/api/mcpThen run /mcp and sign in when it prompts.
Codex CLI
codex mcp add a1 --url https://www.a1.gallery/api/mcpCursor and Claude Desktop
{
"mcpServers": {
"a1": {
"url": "https://www.a1.gallery/api/mcp"
}
}
}VS Code (1.99+ with GitHub Copilot)
{
"servers": {
"a1": {
"type": "http",
"url": "https://www.a1.gallery/api/mcp"
}
}
}Windsurf
{
"mcpServers": {
"a1": {
"serverUrl": "https://www.a1.gallery/api/mcp"
}
}
}Zed (0.168+)
{
"context_servers": {
"a1": {
"url": "https://www.a1.gallery/api/mcp"
}
}
}What you can ask for
"Find three brutalist law firm sites and show me their heroes."
"What type scale do agency heroes actually use?" — quartiles across every site, not one example.
"Show me pricing pages that mention usage-based billing." — full-text search inside the page copy.
"What do portfolio FAQs say about refunds?" — extracted Q&A pairs with frequencies.
"Rebuild this pricing section." — palette, type, spacing and radius as measured values.
Tools
All 17 tools are read-only and annotated readOnlyHint: true.
Websites
Tool | What it does |
| Keyword search across names, descriptions and taxonomy. Resolves aliases — "SaaS", "fintech", "brutalist" map to real taxonomy terms. |
| Filter-only browsing by type, category, style, technology or colour. |
| Everything for one site: fonts, colours, styles, technologies, creator, sections. |
| Inspiration clusters around a given site. |
| Newest additions, publish-date descending. |
| The full taxonomy with counts — use it to build valid filters. |
Sections
Tool | What it does |
| Search inside section copy — headings, FAQ answers, pricing text, testimonials. Returns the screenshot, the extracted structure and the measured tokens. |
| Every captured section for one site, in page order. |
| Aggregate content patterns across many sections — topic distribution, most common verbatim FAQ questions. |
| Aggregate measured values — p25/median/p75 for heading size, body size, scale ratio, padding, container width, radius, plus common typefaces and accent colours. |
Pages
Tool | What it does |
| One page type across the whole gallery — every pricing page, every about page. Full-text searchable. |
| The sub-pages captured for one site. |
Fonts and creators
Tool | What it does |
| Fonts by classification, licence, or the category of site using them. |
| One font — classification, licence, description, usage count. |
| Real-world examples of two fonts used together. |
| Designers and studios, filterable by category or style. |
| One creator: bio, links, featured work. |
Full descriptions, parameters and response shapes come back from tools/list.
Plugin
Installing the connector gives an agent 17 tools. It does not tell the agent that
analyze_design_tokens answers "how big should this be" better than five screenshots, or
that a lowSample flag means stop generalising. The plugin carries that.
Skills
Skill | Fires when |
| A design question needs evidence — type scale, spacing, palette, or what sites of a kind actually do. Routes to the aggregate tools first, examples second. |
| Recreating a hero, pricing table or FAQ. Builds from the measured |
| First connection, or a |
Commands
Command | What it does |
| Real sites matching a design brief, rephrased into the gallery's taxonomy. |
| Measured values for a section type, reported as p25–p75 ranges. |
| Sites using a font or a font pairing. |
Sub-agent
design-researcher handles open briefs that need several searches — an aggregate pass,
a couple of targeted searches, then the values to build with. It returns a brief and never
edits files.
Why aggregates use quartiles
analyze_design_tokens reports p25, median and p75 rather than an average. Design values
are long-tailed — one site with a 180px hero heading drags the mean somewhere useless.
Narrow slices thin out fast. Ask for pricing sections on shops and you may be looking at a
handful of examples. When that happens the response carries lowSample: true and reports
raw counts instead of percentages, so the agent can say "here are four examples" rather
than inventing a norm.
Notes
Site descriptions and section copy are third-party website content. The tool descriptions flag them as untrusted external data.
This repository holds the manifest and the docs. The server itself is closed-source and hosted at a1.gallery.
Support
Issues and questions: open an issue or email hello@a1.gallery.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Curated design references for AI — real CSS values, typography specs, and color palettes.
The taste layer for AI website builders: real design taste from 270+ deeply-analysed sites.
Search curated design styles, real product screens, and user flows for evidence-based design work.
A design-style library for AI agents: search real styles, fetch a ready-to-apply design spec.
Related MCP Servers
- FlicenseAqualityDmaintenanceProvides comprehensive design principles and best practices to help LLMs generate modern, accessible web pages through guidance on layouts, colors, and typography. It enables users to review design approaches and access expert recommendations for responsive design, component structure, and current industry trends.12323
- AlicenseNot gradedqualityCmaintenanceStructured design references from 1,000+ curated websites for AI-powered web design. Retrieve real CSS values, typography specs, color palettes, and design rationale via MCP.MIT
- AlicenseNot gradedqualityDmaintenanceGive your AI coding agent design taste. 104 curated design seeds with colors, fonts, spacing, and shadows. Query by vibe, brand, or style.43MIT
- AlicenseAqualityAmaintenanceAnalyzes and extracts design tokens, assets, and layout from live websites to enable AI clients to faithfully replicate them, with tools for screenshotting, component inspection, and pixel-diff verification.1417MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/bryntay/a1-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server