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/JaminZhou/AppKitInspectorInstalling this writes the configuration, not the program: `./scripts/start-server` has to be on your PATH already, or the server will not start.
Wrote 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/jaminzhou/appkitinspector/appkit-inspector-appkit_inspector)<a href="https://agentmods.dev/mcp/jaminzhou/appkitinspector/appkit-inspector-appkit_inspector"><img src="https://agentmods.dev/badge/mcp/jaminzhou/appkitinspector/appkit-inspector-appkit_inspector/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/jaminzhou/appkitinspector/appkit-inspector-appkit_inspector"><img src="https://agentmods.dev/badge/mcp/jaminzhou/appkitinspector/appkit-inspector-appkit_inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
appkit_inspector 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 1mo 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
{
"appkit_inspector": {
"command": "./scripts/start-server",
"args": [],
"cwd": ".",
"startup_timeout_sec": 10,
"tool_timeout_sec": 30
}
}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.
- 1mo ago First seen · 9 lines scan A 9420cfb5420f
appkit_inspector is an MCP server published in the GitHub repository JaminZhou/AppKitInspector (0 stars, last pushed 5d ago), licensed Apache-2.0. 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 2026-08-31.
Other mcp servers, from other repositories
markview
Native macOS markdown preview with MCP server for Claude Code. Swift/SwiftUI, no Electron. Runs locally from the mcp-server-markview npm package.
agentcastkit
Agent-first screen demo production for macOS, exposed through MCP. Runs locally from the agentcastkit npm package.
xcodebuildmcp
XcodeBuildMCP is a Model Context Protocol server that provides tools for Xcode project management, simulator management, and app utilities. Runs locally from the xcodebuildmcp npm package. Needs 1 environment variable to run.
apple-stocks-mcp
Reads your macOS Apple Stocks watchlist, quotes and fundamentals locally. Read-only, no network. Runs locally from the apple-stocks-mcp npm package.
claude-desktop-to-code
MCP server "claude-desktop-to-code" as configured in abhaymettu/claude-desktop-to-code. Runs locally from the claude-desktop-to-code Python package.
iac-mcp
MCP server "iac-mcp" as configured in jsavin/iac-mcp. Runs /absolute/path/to/iac-mcp/dist/index.js with node. Needs 1 environment variable to run.