Agent Guard MCP server

by ipezygj·io.github.ipezygj/agent-guard·v0.2.1

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

C65/100grade C

What users say

No reviews yet

Safety scan

C65/100

Adoption

Not measured yet

Usage numbers are collected on the next scan

Reviews

Nobody has reviewed Agent Guard yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

check_command
Is a shell command DESTRUCTIVE or a remote-code-exec vector? Call this before running any shell command you're not 100% sure about. Flags recursive force-deletes of root/home, disk wipes (dd/mkfs), pipe-to-shell (curl … | bash), fork bombs, force-push, hard-reset, sudo, DROP TABLE, world-writable perms, and more — with a severity and why.
check_package
Is a package SAFE to install? Call this before `pip install` / `npm install` / adding any dependency. Checks: does it actually exist on the registry (a hallucinated name is a red flag), is it a TYPOSQUAT of a popular package, does it RUN CODE ON INSTALL (npm pre/post-install scripts — the classic supply-chain malware vector), and is it in a known MALWARE / vulnerability advisory (OSV). ecosystem =
scan_secrets
Does this text/code LEAK a secret? Call this before you commit, paste, log, or output code or config. Detects API keys (AWS/OpenAI/Anthropic/Google/Stripe/GitHub/Slack), private-key blocks, JWTs, and generic `password=/api_key=` assignments — returns each finding (type, line, redacted).

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings

Code scan5 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancerepository not readable: repo not found3/15
Maintainer identityno repository or website to verify2/10

Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

claude mcp add agent-guard -- uvx agent-tripwire

Is Agent Guard MCP server safe?: With care: it is graded C, so read the findings first (65/100). Read the Agent Guard safety report
How do I install Agent Guard?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Agent Guard need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Guard maintained?: The latest release is v0.2.1.
What can I use instead of Agent Guard?: Servers from other publishers that do the same job: Doc Bridge MCP server, MCP server and IWE MCP server. Compare all Agent Guard alternatives.

Same job from other publishers: the closest match first, then the best rated.

Doc Bridge
Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
not reviewed
Growing
A
MCP
Authorize consequential AI agent actions before execution
not reviewed
Established
A
IWE
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
not reviewed
Established
A
Orcareplay
Read, replay and fork recorded coding-agent runs.
not reviewed
Established
A
HOL Guard
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
not reviewed
Established
A