Ext Ops Panel
Open dashboard
Comparison

saferun-guard vs Agent Guardrails

saferun-guard is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑19.

saferun-guard is a plugin bundle for AI coding tools published by Cocabadger. No marketplace we read lists it any more. Agent Guardrails is an MCP server published by logi-cmd. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-23. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacesaferun-guardAgent Guardrails
Community marketplace cocabadger/saferun-guard Removed on 2026-10-19
Version: 0.1.0
Forks (GitHub): 0
Stars (GitHub): 4
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.3.3
Downloads/month (npm): 441
Downloads/week (npm): 53
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

saferun-guard vs Agent Guardrails
Factsaferun-guardno longer listed · Agent Guardrails
Marketplaces that list it (differs)01
Stars (GitHub) (differs)4No figure on GitHub
Forks (GitHub) (differs)0No figure on GitHub
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (agent-guardrails)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Hooks it runs (differs)3Not published
Parts of the bundle (differs)4Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/cocabadger/saferun-guardNot stated
Changes in the last 7 days (differs)20
First seen (differs)2026-10-152026-10-11

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of saferun-guard

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • codeguard-security

    Comprehensive security rules for AI coding agents

    by Project CodeGuard · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • sage

    Agent Detection & Response (ADR) for Claude Code — guards commands, files, and web requests

    by Gen Digital · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • hs

    Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.

    by frmoretto · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • agentguard

    AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.

    by GoPlus Security · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • trajectory-security

    AI Guard and AI-EDR security controls for coding agents, powered by Trajectory

    by Datadog · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • aport-guardrails

    Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…

    by aporthq · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

saferun-guard

In its own words, on Community GitHub marketplaces:

Runtime safety firewall for AI coding agents. Blocks dangerous commands and protects sensitive files before they execute.

Agent Guardrails

In its own words, on Official MCP Registry:

Merge gates and safety checks for AI coding agents via MCP.

How to run each

saferun-guard

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Agent Guardrails As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio agent-guardrails -- npx -y agent-guardrails

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: saferun-guard · What it can do: Agent Guardrails · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built