Icons8
CommunityGet access to MCP server SVG and MCP server PNG icons in your vibe-coding projects
| Publisher | null |
| Repository | null |
| Language | TypeScript |
| Forks | 0 |
| Stars | 795 |
| Available tools | 4 |
| Transport type | streamable-http |
| Categories | |
| License | MIT |
- Connect tools to AI workflows
Icons8 exposes MCP capabilities that can be used by compatible AI clients and agents.
- 4 available tools
Browse the callable actions below, including names and descriptions when provided by the server.
- Ready-to-copy setup
Use the installation snippets to configure this server in your preferred MCP client.
- Open source signals
795 stars and 0 forks from the linked repository.
Installation
{
"mcpServers": {
"icons8mcp": {
"url": "https://mcp.icons8.com/mcp/"
}
}
}Available Tools
- search_icons
$2d
- list_categories
List all available icon categories.
Args: ctx: MCP context for API access limit: Maximum number of results to return (default: 10) page: Page number for pagination (default: 1)
Returns: List of icon categories with subcategories
- list_platforms
List all available icon platforms/styles.
Args: ctx: MCP context for API access limit: Maximum number of results to return (default: 100) page: Page number for pagination (default: 1)
Returns: List of icon platforms/styles
- get_icon_png_url
Get a PNG URL for an icon by its ID - use when SVG is not available. NOTE: SVG format is preferred for Icons8 icons when possible (use get_icon_svg).
Args: icon_id: The unique identifier of the icon ctx: MCP context for API access size: The preview image size in pixels (default: 24)
Returns: Dictionary containing the PNG preview URL
Use Icons8 MCP with multiple AI models
TypingMind connects MCP tools at the workspace level, so once Icons8 is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP connects through a hosted MCP server URL in TypingMind.
Add an MCP server URL
Use this when Icons8 is already hosted remotely or your team wants one shared connector that multiple users can access.
Open MCP connectors
In TypingMind, go to Plugins, open MCP connectors, then choose Add URL.
- Open TypingMind in your browser.
- Go to Plugins.
- Open MCP connectors.
- Click Add URL.

Paste the server URL
Enter https://mcp.icons8.com/mcp/ in the Server URL field. Add a connection name, description, icon, custom HTTP headers, or OAuth client settings if the server requires them.
- Paste https://mcp.icons8.com/mcp/ into the Server URL field.
- Enter a connection name for Icons8.
- Add a description and icon if you want it to be easier to identify.
- Add custom HTTP headers or OAuth client details if the server requires authentication.
Create the connection
Click Create connection, then return to the Plugins list and confirm the new MCP connection is active.
- Click Create connection.
- Return to the MCP connectors list.
- Confirm the Icons8 connection appears as active.
- Refresh the plugin list if the connection does not appear immediately.
Switch models without reconnecting
Start a chat with your preferred model, enable the Icons8 tools from Plugins, and switch to another model whenever needed. The MCP connection stays available to the TypingMind workspace.
- Start a new chat in TypingMind.
- Select the AI model you want to use.
- Enable the Icons8 tools from Plugins.
- Ask the model to use the tool when needed.
- Switch to another AI model and reuse the same MCP connection.

Here is what I found using Icons8.
Frequently asked questions
What is the Icons8 MCP server used for?
Icons8 is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.
Can I use Icons8 MCP with multiple AI models in TypingMind?
Yes. TypingMind connects MCP tools at the workspace level, so you can use Icons8 with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.
Why use Icons8 MCP with TypingMind?
TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Icons8 connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.
How do I connect Icons8 MCP to TypingMind?
Icons8 can be connected in TypingMind by adding its hosted MCP server URL. This is useful when you want a remote MCP connection that is available from your TypingMind workspace.
What tools does Icons8 MCP provide in TypingMind?
Icons8 exposes 4 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.
Do I need to share my API keys with TypingMind to use Icons8 MCP?
No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Icons8 requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.
Related MCP Servers
View allFigma Context
MCP server to provide Figma layout information to AI coding agents like Cursor
Magic
It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
shadcn/ui
A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable with react,svelte 5,vue & React Native
Figma
A guide on how to use the Figma MCP server
