mcp-airlock runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 16 Sep 2026.
Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit
We read the source, 20 h ago · rules 3dff92dd89df
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.
up = subprocess.Popen([sys.executable, "-m", "tests.fake_upstream"], env=env)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 mcp-airlock -- uvx mcp-airlock
{
"mcpServers": {
"mcp-airlock": {
"args": [
"mcp-airlock"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-airlock]
command = "uvx"
args = ["mcp-airlock"]
{
"mcpServers": {
"mcp-airlock": {
"args": [
"mcp-airlock"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-airlock": {
"args": [
"mcp-airlock"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
AIRLOCK_JWT_SECRET (HS256 secret for verifying bearer tokens (or set AIRLOCK_JWKS_URL for OIDC)), AIRLOCK_SECRET (Key for signing confirmation tokens; set it when running more than one replica).
The author declared them in the registry entry; get the values from the project itself.
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
Runtime proxy for MCP security, cost governance & audit
MCP server that sends mail over SMTP, gated behind an allowlist and a human confirmation
Static blast-radius audit for MCP servers before agent install. Manifest optional.
Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.
Security, cost, and health governance proxy for MCP infrastructure
Answers built from our own checks of this server.