Haldir runs on your own machine — the client starts it, so there is no endpoint to ping. 118 installs a week from pypi. Last commit 4 Oct 2026.
Guardian layer for AI agents: identity, secrets, audit via MCP.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
r = subprocess.run(args, cwd=ROOT)
src = os.path.join(ROOT, d)
…e-title">Webhooks</h2><div class="form-row" style="max-width:500px"><input type="text" id="wh-url" placeholder="https://hooks.slack.com/..." onkeydown="if(event.key==='Enter')addWH()"><button onclick="addWH()">Add</button></div><table><thead><tr><th>URL</th><th>Events</th><th>Fir…
…'audit-empty');if(!d.entries||!d.entries.length){b.innerHTML='';e.style.display='block';return}e.style.display='none';b.innerHTML=d.entries.map(function(x){var c=x.flagged?' class="flagged"':'';var t=new Date(x.timestamp*1000).toLocaleTimeString();var fl=x.flagged?'<span style="c…
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add haldir -- uvx haldir{
"mcpServers": {
"haldir": {
"command": "uvx",
"args": [
"haldir"
]
}
}
}[mcp_servers.haldir]
command = "uvx"
args = ["haldir"]{
"mcpServers": {
"haldir": {
"command": "uvx",
"args": [
"haldir"
]
}
}
}{
"servers": {
"haldir": {
"type": "stdio",
"command": "uvx",
"args": [
"haldir"
]
}
}
}Alternatives to Haldir
same job, measured the same wayAI Agent Guardrails MCP server - security layer
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
Security audit for AI agents: code, deps, exposure, secrets, drift, SBOM, and IoC.
BridgeGuard MCP Server - Cross-chain bridge security audit tools for AI coding agents. Scan bri...
Security guardrails for AI agent payments
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
OS keychain secrets for AI coding agents, over MCP.
Haldir — questions
Answers built from our own checks of this server.