Agent Runtime Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from npm. Last commit 3 Nov 2026.
Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
What the code does
We read the source, 39 min ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
{ pattern: /(?:chmod|chown)\s+[0-7]*777/, weight: 2, label: 'chmod 777 (overly permissive)' },
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.
{ pattern: /cat\s+(?:~\/)?\.ssh\/id_rsa/, weight: 7, label: 'SSH private key read' },
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Agent Runtime Guard and you get told the day something new turns up.
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 agent-runtime-guard -- npx -y agent-runtime-guard{
"mcpServers": {
"agent-runtime-guard": {
"command": "npx",
"args": [
"-y",
"agent-runtime-guard"
]
}
}
}[mcp_servers.agent-runtime-guard]
command = "npx"
args = ["-y", "agent-runtime-guard"]{
"mcpServers": {
"agent-runtime-guard": {
"command": "npx",
"args": [
"-y",
"agent-runtime-guard"
]
}
}
}{
"servers": {
"agent-runtime-guard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-runtime-guard"
]
}
}
}Alternatives to Agent Runtime Guard
same job, measured the same wayLocal spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Routes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
18 tools: agent memory, API drift detection, and HMAC-signed trust receipts
Agent Runtime Guard — questions
Answers built from our own checks of this server.