About iconmind
iconmind is an offline MCP server for AI assistants building user interfaces. It searches the bundled IconMind icon set and returns valid icon slugs and import lines.
Key features
- 01Offline icon data
- 02Search by name, tag, alias, or category
- 03Return icon slugs and import lines
Use cases
- 01Find an icon while building a UI
- 02Check an icon name before adding an import
MCP support
Exposes IconMind icon search to MCP clients, including search by name, tag, alias, or category, with slugs and import lines in the results.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
4Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | |
| query | string | Yes | Keyword or concept, e.g. 'vector database', 'agent memory' |
| category | enum | No | Restrict to one domainai | agents | mcp | rag | data | devops | cloud | security | automation | analytics | devtools | interface | commerce | finance | travel | weather | health | education | home | social |
Details
From the project README@iconmind/mcp
An MCP server for IconMind, so an AI assistant writing your UI can search the real icon set instead of guessing icon names that do not exist.
claude mcp add iconmind -- npx -y @iconmind/mcp
Any other MCP client takes the same command in its config — Cursor and Windsurf in mcp.json,
VS Code under "servers" in .vscode/mcp.json, Codex in ~/.codex/config.toml:
{ "mcpServers": { "iconmind": { "command": "npx", "args": ["-y", "@iconmind/mcp"] } } }
Listed in the MCP registry as io.github.Iconmind/iconmind; the docs are at
https://iconmind.dev/docs/mcp/.
- Runs offline — the icon data is bundled
- Starts in well under a second
- Search by name, tag, alias, or category; returns real slugs and import lines
MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.