Aegis runs on your own machine — the client starts it, so there is no endpoint to ping. 136 installs a week from npm. Last commit 6 Aug 2026.
Credential isolation for AI agents. Inject secrets at the network boundary.
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.
? path.join(config.dataDir, info.dbPath)
hint: `Update scopes with: aegis vault update --name ${credential.name} --scopes ${scopeList},${reqMethod === 'GET' ? 'read' : 'write'}`,
execFileSync(which, [command], { stdio: 'pipe' });
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 aegis -e 'AEGIS_MASTER_KEY=<AEGIS_MASTER_KEY>' -e 'AEGIS_SALT=<AEGIS_SALT>' -- npx -y @getaegis/cli{
"mcpServers": {
"aegis": {
"command": "npx",
"args": [
"-y",
"@getaegis/cli"
],
"env": {
"AEGIS_MASTER_KEY": "<AEGIS_MASTER_KEY>",
"AEGIS_SALT": "<AEGIS_SALT>"
}
}
}
}[mcp_servers.aegis]
command = "npx"
args = ["-y", "@getaegis/cli"]
env = { AEGIS_MASTER_KEY = "<AEGIS_MASTER_KEY>", AEGIS_SALT = "<AEGIS_SALT>" }{
"mcpServers": {
"aegis": {
"command": "npx",
"args": [
"-y",
"@getaegis/cli"
],
"env": {
"AEGIS_MASTER_KEY": "<AEGIS_MASTER_KEY>",
"AEGIS_SALT": "<AEGIS_SALT>"
}
}
}
}{
"servers": {
"aegis": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@getaegis/cli"
],
"env": {
"AEGIS_MASTER_KEY": "<AEGIS_MASTER_KEY>",
"AEGIS_SALT": "<AEGIS_SALT>"
}
}
}
}Put your own values in place of
<AEGIS_MASTER_KEY> (Master encryption key for the credential vault), <AEGIS_SALT> (Hex-encoded 32-byte salt for key derivation (generated by aegis init)).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
AEGIS_DATA_DIR (Directory for vault databases and registry (default: .aegis/)), AEGIS_PORT (Gate proxy port (default: 3100)), AEGIS_LOG_LEVEL (Log verbosity: debug, info, warn, error (default: info)), AEGIS_LOG_FORMAT (Log output format: json or pretty (default: json)), AEGIS_VAULT (Named vault to use (default: default)), AEGIS_REQUIRE_AGENT_AUTH (Require agent authentication on every request (true/false, default: false)), AEGIS_POLICY_MODE (Policy enforcement mode: enforce, dry-run, or off (default: enforce)), AEGIS_POLICIES_DIR (Directory containing YAML policy files), AEGIS_METRICS (Enable Prometheus metrics endpoint (true/false, default: true)).
Alternatives to Aegis
same job, measured the same waySecret broker for agents: reference secrets by name; values injected only at the execution boundary.
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Encrypted secrets and credential management for agents
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.
Aegis — questions
Answers built from our own checks of this server.