Agent Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 33 installs a week from pypi.
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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-guard -- uvx agent-tripwire{
"mcpServers": {
"agent-guard": {
"args": [
"agent-tripwire"
],
"command": "uvx"
}
}
}[mcp_servers.agent-guard]
command = "uvx"
args = ["agent-tripwire"]{
"mcpServers": {
"agent-guard": {
"args": [
"agent-tripwire"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"agent-guard": {
"args": [
"agent-tripwire"
],
"command": "uvx"
}
}
}Alternatives to Agent Guard
same job, measured the same wayCheck text for leaked credentials before an agent writes or commits it. Runs locally.
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Build and manage policy-compliant AI agents with safety enforcement and compliance checking
Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
Scaffold Starter Series projects and check release, deployment, security, and agent instructions.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Agent Guard — questions
Answers built from our own checks of this server.