Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ethbak/icon-composer-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/ethbak/icon-composer-mcp/icon-composer)<a href="https://agentmods.dev/mcp/ethbak/icon-composer-mcp/icon-composer"><img src="https://agentmods.dev/badge/mcp/ethbak/icon-composer-mcp/icon-composer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/ethbak/icon-composer-mcp/icon-composer"><img src="https://agentmods.dev/badge/mcp/ethbak/icon-composer-mcp/icon-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
icon-composer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"icon-composer": {
"command": "npx",
"args": [
"-y",
"icon-composer-mcp"
]
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 9 lines scan A 4f3c4fd9beb2
icon-composer is an MCP server published in the GitHub repository ethbak/icon-composer-mcp (45 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
app-store-connect-mcp
MCP server "app-store-connect-mcp" as configured in imfaisii/asc-mcp. Runs locally from the app-store-connect-mcp npm package.
app-publisher-mcp
MCP server for vibe coders - AI app icon generation, auto-resizing for iOS/Android, and store publishing automation. Runs locally from the @seungmanchoi/app-publisher-mcp npm package.
apple-dev-mcp
Complete Apple development guidance: Human Interface Guidelines (design) + Technical Documentation for iOS, macOS, watchOS, tvOS, and visionOS. Runs locally from the apple-dev-mcp npm package.
ui-debugger-mcp
Autonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues. Runs locally from the @developerz.ai/ui-debugger-mcp npm package. Needs 2 environment variables to run.
vrchat-mcp
VRChat MCP Server - Access VRChat API through Model Context Protocol. Runs locally from the vrchat-mcp npm package.
sequential-thinking
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.