Heimdall runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from npm. Last commit 6 Jul 2026.
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
What the code does
We read the source, 7 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.
child = spawn(command, args, {
function mkChecks(id, info, cls) { $(id).innerHTML = Object.entries(info).map(([k,[l]]) => `<label style="font-size:13px;display:flex;align-items:center;justify-content:flex-start;gap:8px;width:100%;cursor:pointer"><input type="checkbox" class="${cls}" value="${k}" style="flex:…
test: /\.ssh\/|\bid_rsa\b|\bid_ed25519\b|\.aws\/credentials|\bboto3\b|\bkeyring\b|GOOGLE_APPLICATION_CREDENTIALS|\.netrc\b/i,
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 heimdall -- npx -y mcp-heimdall-scan{
"mcpServers": {
"heimdall": {
"command": "npx",
"args": [
"-y",
"mcp-heimdall-scan"
]
}
}
}[mcp_servers.heimdall]
command = "npx"
args = ["-y", "mcp-heimdall-scan"]{
"mcpServers": {
"heimdall": {
"command": "npx",
"args": [
"-y",
"mcp-heimdall-scan"
]
}
}
}{
"servers": {
"heimdall": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-heimdall-scan"
]
}
}
}Alternatives to Heimdall
same job, measured the same wayMulti-layer security scanner for MCP servers and agent skills (injection, exfiltration)
Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
Scan MCP servers and agent tool manifests for poisoning, exfiltration, secrets and supply-chain risk
An MCP server that provides image generation and editing capabilities
Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.
Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
Unified MCP server for AgenticLens and Agentic Chaos capabilities.
Heimdall — questions
Answers built from our own checks of this server.