haldir
Level CLocalThe guardian layer for AI agents — identity, secrets, audit via MCP. Gate + Vault + Watch.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"haldir": {
"command": "npx",
"args": [
"haldir"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/ExposureGuard/haldir
Known working client config (can write into mcp.json):
{
"mcpServers": {
"haldir": {
"command": "npx",
"args": [
"haldir"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
ExposureGuardDomain security scanning for AI agents. A-F grades, 8 checks, fix snippets.NetdataReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anoToolJetOpen-source foundation of ToolJet AI - the enterprise app generation platform fosignozSigNoz is an open-source, OpenTelemetry-native observability platform for your tSkillSpectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patternskuboard-pressKuboard v4 官方文档(zh/en 双语):Kuboard 是基于 Kubernetes 的微服务管理界面。本仓库为 v4 版本文档站源码,涵盖安装升级