Trackly CLI
v0.18.1
MCP ServerMCP Registry
io.github.trackly-app/trackly
AI job search for Claude, ChatGPT, Cursor. 170K+ jobs, 3,800+ companies. OAuth or stdio.
stdiostreamable-httpnpmregistry 收录
io.github.qingxuantang/tar-engine · v0.3.3
Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.
TAR Engine 是一个MCP Server，收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"tar-engine": {
"command": "uvx",
"args": [
"tar-engine"
]
}
}
}TAR_ENGINE_URL可选Override the audit backend. Default is the hosted playground at https://tarai.dev. Set to http://localhost:8765 (or your own tar-engine deployment) to self-host and keep SKILL.md content on your machine.
TAR_ENGINE_BYOK_OPENAI_KEY可选secretOpenAI API key that unlocks the semantic LLM and adversarial prompt-fuzz layers. Static and supply-chain layers run without it.
TAR_ENGINE_BYOK_ANTHROPIC_KEY可选secretAnthropic API key alternative to the OpenAI key for the semantic and adversarial layers.
v0.18.1
io.github.trackly-app/trackly
AI job search for Claude, ChatGPT, Cursor. 170K+ jobs, 3,800+ companies. OAuth or stdio.
v0.3.0
io.github.theoddden/stamp
NTP time plus clock-drift history: stable vs. accelerating offsets.
v0.1.13
io.github.Servosity/ninjaone-mcp
Every NinjaOne report, plus a local store that answers fleet-wide questions no single API call can
v0.81.0
io.github.ArtJack/verdict
Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
v0.3.3
io.github.toki0413/saturday-materials
Materials computing tools for AI agents: structures, engines, phonons, EOS, NEB, sampling, lineage.
v2.1.0
com.notepom/notepom
Persistent workspace and visual memory for humans and autonomous agents.
{
"id": "io.github.qingxuantang/tar-engine",
"type": "mcp-server",
"version": "0.3.3",
"displayName": "TAR Engine",
"description": "Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.",
"repository": {
"url": "https://github.com/qingxuantang/tar-engine",
"source": "github"
},
"homepage": "https://tarai.dev",
"distribution": {
"packages": [
{
"registryType": "pypi",
"identifier": "tar-engine",
"version": "0.3.3",
"runtimeHint": "uvx",
"transport": "stdio",
"environmentVariables": [
{
"name": "TAR_ENGINE_URL",
"description": "Override the audit backend. Default is the hosted playground at https://tarai.dev. Set to http://localhost:8765 (or your own tar-engine deployment) to self-host and keep SKILL.md content on your machine."
},
{
"name": "TAR_ENGINE_BYOK_OPENAI_KEY",
"description": "OpenAI API key that unlocks the semantic LLM and adversarial prompt-fuzz layers. Static and supply-chain layers run without it.",
"isSecret": true
},
{
"name": "TAR_ENGINE_BYOK_ANTHROPIC_KEY",
"description": "Anthropic API key alternative to the OpenAI key for the semantic and adversarial layers.",
"isSecret": true
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"trae",
"cherry-studio",
"lingma",
"windsurf",
"cline",
"workbuddy"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.qingxuantang/tar-engine",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.qingxuantang%2Ftar-engine/versions/latest",
"isOfficial": true,
"status": "active"
}
}