agentguard runs on your own machine — the client starts it, so there is no endpoint to ping. 48 installs a week from npm.
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
The linked repository no longer exists on GitHub — it was deleted or made private.
We read the source, 16 d ago · rules ccca72095570
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.
пакет @agentwares/agentguard ссылается на agentwares/agentwares
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
- name: Create or update the release
env:
GH_TOKEN: ${{ github.token }}
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 agentguard -- npx -y @agentwares/agentguard
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@agentwares/agentguard"
]
}
}
}
[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@agentwares/agentguard"]
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@agentwares/agentguard"
]
}
}
}
{
"servers": {
"agentguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentwares/agentguard"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
AGENTGUARD_CONFIG (Path to agentguard.yaml (default ./agentguard.yaml). If unset and that file does not exist, agentguard serves only its own read-only tools: agentguard_get_status, agentguard_get_report, agentguard_verify_audit_log), AGENTGUARD_KILL (Set to 1 to halt every tool call (kill switch)).
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Local MCP proxy for tool restrictions, response redaction, audit logs, and database schema context.
MCP server for MikroTik RouterOS and SwOS: typed tools, dry-run, RBAC, audit logs, and rollback.
Answers built from our own checks of this server.