IconsDB launches an AI-powered semantic search engine and remote MCP server spanning over 200,000 open-source icons for developers and coding agents.

// 2h agoPRODUCT LAUNCH

IconsDB launches an AI-powered semantic search engine and remote MCP server spanning over 200,000 open-source icons for developers and coding agents.

IconsDB is an AI-powered semantic icon search platform and remote Model Context Protocol (MCP) server providing access to more than 200,000 icons, logos, and emoji across 83 open-source libraries, including Lucide, Heroicons, Phosphor, and Material Symbols. Instead of guessing exact icon names, developers can describe concepts using natural language queries (such as "sad robot" or "money leaving") and immediately receive paste-ready code for React, Vue, Svelte, Solid, SVG, or CSS. Built specifically to empower agentic workflows, IconsDB connects to coding agents such as Claude Code, Cursor, and VS Code Copilot to inspect existing project dependencies and serve consistent, importable icons with zero local installation or API key setup.

// ANALYSIS

Coding agents regularly hallucinate icon names and mix incompatible design sets, making semantic, package-aware MCP tooling a high-leverage upgrade for agentic UI development.

–Eliminates icon hallucinations: Prevents LLMs from guessing invalid component names by resolving queries to verified assets and exact npm export paths.
–Effortless agent integration: Operates via a remote Streamable HTTP MCP endpoint requiring no API keys or local background daemons.
–Centralized library coverage: Aggregates 83 open-source icon sets, allowing developers and agents to enforce visual consistency across an entire UI.
–Multi-framework exports: Generates ready-to-paste snippets in SVG, CSS, inline components, and major frontend framework packages.

// TAGS

iconsai-searchmcpdeveloper-toolsfrontenddesign-systemsopen-source

DISCOVERED

2h ago

2026-09-23

PUBLISHED

8h ago

2026-09-23

RELEVANCE

8/ 10

AUTHOR

Musthaq Ahamad

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE1h ago

Grok Imagine introduces granular image controls for AI video creation

Grok Imagine has rolled out a powerful new feature for video creation that allows users to dictate exactly how uploaded images are utilized within the generated video. Instead of relying on a single image prompt, users can now designate uploaded images to serve specific roles, such as the first frame, an intermediate frame, the last frame, a seamless loop, or a stylistic reference.

MODEL1h ago

Anthropic launches Claude Opus 5.5, bringing adaptive reasoning, 30% faster output speeds, and a 40% cost reduction over its predecessor.

Anthropic has released Claude Opus 5.5, the first model in their new 5.5 family designed specifically for complex, agentic work like coding and long-running tasks. The model matches the performance of Claude Fable 5.1 on most tasks while offering significant efficiency gains, including a 40% reduction in operating costs compared to Opus 5 and 30% faster generation speeds. It also introduces "adaptive thinking" to dynamically adjust reasoning effort based on task complexity.

OPEN SOURCE1h ago

Laya-MLX brings rapid, local, typed-decision AI to Apple Silicon via MLX.

A new Apple Silicon port, Laya-MLX, introduces Laya's typed-decision AI directly to the MLX framework for fully local execution. Instead of traditional token-by-token text generation, the model directly yields typed decisions and probabilities across options, achieving AI decision times as fast as 7.4 milliseconds on Mac.