Icon Mcp

Created By
agentic-ph10 months ago
A powerful Model Context Protocol (MCP) server that provides unified search capabilities across multiple icon libraries with fuzzy search, intelligent caching, and comprehensive filtering options.
Overview

What is Icon MCP?

Icon MCP is a powerful Model Context Protocol (MCP) server that provides unified search capabilities across multiple icon libraries, featuring fuzzy search, intelligent caching, and comprehensive filtering options.

How to use Icon MCP?

To use Icon MCP, install it via NPM or clone the repository from GitHub. Start the server using the command npm start and configure it through environment variables.

Key features of Icon MCP?

  • Multi-library support for simultaneous searches across various icon libraries.
  • Fuzzy search capabilities for typo tolerance.
  • Intelligent caching for fast response times.
  • Comprehensive filtering options by library, style, category, and tags.
  • NPM package integration for automatic icon library management.
  • Full TypeScript support for type safety.

Use cases of Icon MCP?

  1. Developers can quickly find icons from multiple libraries for their applications.
  2. Designers can search for specific icons using fuzzy matching to accommodate typos.
  3. Teams can manage and integrate icon libraries efficiently in their projects.

FAQ from Icon MCP?

  • Can Icon MCP search across all icon libraries?
    Yes! Icon MCP allows searching across multiple libraries simultaneously.

  • Is there a way to customize the search parameters?
    Yes! You can configure search parameters such as cache TTL and search limits through environment variables.

  • How do I troubleshoot if the server doesn't start?
    Check if the package is installed correctly and ensure you have the necessary permissions.

Server Config

{
  "mcpServers": {
    "icon-search": {
      "command": "npx",
      "args": [
        "icon-mcp"
      ],
      "env": {
        "CACHE_TTL": "300000",
        "DEFAULT_SEARCH_LIMIT": "50",
        "LOG_LEVEL": "info"
      }
    }
  }
}
Project Info
Created At
10 months ago
Updated At
10 months ago
Author Name
agentic-ph
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago