Gatekeeper runs on your own machine — the client starts it, so there is no endpoint to ping. 41 installs a week from npm. Last commit 5 Sep 2026.
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
We read the source, 1 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.
spawn(command, args, { detached: true, stdio: 'ignore' }).unref();
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 gatekeeper -- npx -y @runestone-labs/gatekeeper-mcp
{
"mcpServers": {
"gatekeeper": {
"args": [
"-y",
"@runestone-labs/gatekeeper-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.gatekeeper]
command = "npx"
args = ["-y", "@runestone-labs/gatekeeper-mcp"]
{
"mcpServers": {
"gatekeeper": {
"args": [
"-y",
"@runestone-labs/gatekeeper-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gatekeeper": {
"args": [
"-y",
"@runestone-labs/gatekeeper-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GATEKEEPER_ROLE (Policy role this server presents to Gatekeeper for every call. Required.), GATEKEEPER_URL (Base URL of the Gatekeeper server. Default http://127.0.0.1:3847.), GATEKEEPER_AGENT_NAME (Agent name recorded in Gatekeeper audit logs. Default mcp-client.), GATEKEEPER_RUN_ID (Optional run-correlation id so calls count toward one per-run budget.).
The author declared them in the registry entry; get the values from the project itself.
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
Deterministic policy enforcement and MCP management for AI agent tool calls.
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Zero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.
Answers built from our own checks of this server.