Icons8
The Icons8 MCP Server provides direct access to a library of over 40,000 icons right from your code editor.
You can use natural language prompts to find and insert icons into your projects, either as high-resolution PNGs or scalable SVGs.
Features
π¨ 40,000+ icons across multiple styles, including filled, outlined, color, and iOS glyph
π± Multiple formats – PNG icons for free users, SVG for paid subscribers
π€ AI-powered search – describe icons in natural language and get relevant results
β‘ Real-time integration – icons load directly into your projects without manual downloads
π§ Multiple editor support – works with Claude Code, Cursor, Windsurf, VS Code, and other MCP-compatible tools
π Free tier available – PNG icons work without API key, just requires attribution
π― Context-aware suggestions – AI understands your project context and suggests appropriate icons
How to Use It
1. The MCP server offers two tiers. The free plan provides high-resolution PNG icons, which is great for testing and quick prototypes. The paid plan gives you an API key to access SVG icons.
Free PNG Configuration:
{
"mcpServers": {
"icons8mcp": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.icons8.com/mcp/"
]
}
}
}Paid SVG Configuration (API Key Required):
{
"mcpServers": {
"icons8mcp": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.icons8.com/mcp/",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer YOUR_API_KEY"
}
}
}
}2. Set up your MCP clients.
Claude Code:
```bash
claude mcp add icons8mcp -- \
npx mcp-remote \
"https://mcp.icons8.com/mcp/" \
--header "Authorization: Bearer YOUR_API_KEY"
Cursor:
- Navigate to
Settings->Cursor Settings. - Go to the
MCPtab. - Click
+ Add new global MCP server. - Paste the appropriate JSON configuration (Free or Paid) and save.
Windsurf:
- Navigate to
Settings->Windsurf Settings. - Find the
MCPsection. - Click
Manage plugins + View raw config. - Enter the JSON configuration and save.
VS Code:
- Open
Settings(β, on macOS). - Search for “MCP” and select
Edit in settings.json. - Add the JSON configuration to your
settings.jsonfile. - Restart VS Code if the server does not appear in the agent selection tool menu (β₯βB).
3. Once configured, you can prompt your AI assistant directly. Try a request like, "create a dashboard with analytics SVG icons in a color style" or "add a user icon to this button." The AI will use the Icons8 MCP server to fetch and insert the icons.
FAQs
Q: What do I do if the server says “No API key”?
A: This message appears when you request SVG icons without a valid API key. You can either stick to PNG icons, which are free, or subscribe to an Icons8 plan to get a key for SVG access.
Q: Can I request specific icon styles?
A: Yes, you can specify styles like “filled,” “outlined,” “color,” “iOS glyph,” or other Icons8 style categories in your requests.
Q: My AI assistant isn’t finding the MCP server after installation.
A: Restart your AI coding tool after adding the MCP server configuration. Check that Node.js is installed and accessible from your terminal.
Latest MCP Servers
Apify
Blueprint
HOPX
Featured MCP Servers
Apify
Blueprint
Monday.com
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.



