"Phosphor Icons" matching MCP servers:

lucide-icons-mcp

Description: Supericons MCP lets AI coding agents search, recommend, and retrieve SVG icons from a semantic registry of 20,000+ icons.

Generates software and app icons locally as PNG, ICO, or ICNS files with customizable styles, shapes, gradients, text, and shadows, requiring no external APIs or network access.

Visual icon search, retrieval, and comparison for AI agents. Search 200k+ icons semantically, render side-by-side comparison grids, and retrieve raw SVG markup — all tools return images so vision-capable LLMs can see the icons.

Search 161,000+ free hand-drawn Infyicon icons in four matching styles and fetch ready-to-embed SVG markup or PNG URLs, plus CSS class lookup for the 61,000-glyph Infyicon UI webfont. Free with attribution, no API key required.

Enables creation of infrastructure and architecture diagrams as code using the Python diagrams library, supporting 15+ cloud providers, 500+ node types, custom icons, and flowcharts with multiple output formats.

heroicons-mcp is a Model Context Protocol (MCP) server that exposes Heroicons. It allows LLMs and agentic applications to search, list, and generate usage examples of icons in React applications.

Brings Tabler icons, UI components, page layouts, themes, and live documentation into MCP-compatible AI assistants for correct, hallucination-free usage.

Connects AI assistants to the Itcons.app business operations platform for managing work reports, work orders, projects, clients, and users. It supports both local stdio and remote HTTP modes, enabling querying, searching, and creating operational data with secure authentication.

A search service based on multiple image APIs and icon generation capabilities, specifically designed for integration with Cursor MCP service. Supports image search, download, and AI-generated icons.

Enables agents to generate and edit images, sprites, icons, and animated sprite sheets via Gemini's Nano Banana model. It uses the existing Gemini plan's quota without per-image costs.

A design harness for AI coding agents. Better Design gives an agent design systems, UI and UX principles, icons and UI review: it finds or creates a design system that fits the product and installs its components, explains how sign-up, forms and onboarding should work, and reviews finished screens for readability, accessibility and unclear copy.

Open-source multiplayer design canvas (alternative to Paper.design) with a built-in MCP server. Agents create and stream HTML artboards live next to human collaborators, review them via screenshots, comment on elements, search icons/images/logos and follow shared design guidelines.

Provides unified search across multiple icon libraries with fuzzy search, caching, and comprehensive filtering for easy icon discovery and retrieval via the Model Context Protocol.

Enables AI assistants and coding tools to turn a few lines describing a system into clean, hand-sketched architecture diagrams in a consistent style, saving them as SVG or PNG files. Supports themes, automatic product icons, groups, sequence diagrams and cloud icon packs.

Connects coding agents to a catalogue of real product screens so they can resolve open layout, state, and interaction questions with inline reference images, and fetch the fonts, icons, or animated icon roles a design system lacks along with each item's recorded license. It also returns the colours, typography, components, and provenance behind any web screen already picked, and serves bundled design-workflow documents, playbook prompts, and connection diagnostics without a token.

Enables AI assistants to compile, validate, and explore D2 diagrams using the official D2 WASM package. It provides tools for generating SVGs with custom layouts, themes, and icons directly from D2 source code.

Enables coding agents building UI to fetch real product screens as inline images, pull typed design references, and find licensed fonts, icons, or animated icons when a visual question is unresolved. It also serves a bundled design workflow, command playbooks, and connection diagnostics.

Connects coding agents to a catalogue of real product screens so they can pull concrete UI references, fonts, icons, and the recorded design systems behind web screens when a visual question is open. It also serves bundled design-workflow documents, help, and connection diagnostics for grounding UI work in real products rather than generic templates.

Enables coding agents to find real product screen references, fonts, icons, and recorded design-system details for UI work. It also exposes bundled design workflow resources, command prompts, and connection diagnostics.