AI Guard
MCP serverChecks JS/TS written by AI for risky patterns, fake npm packages and weakened tests
Runs locally- 1 tool
- Open source
- Developer tools
Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests
Runs locallyMCP server to validate Guard Core SecurityConfig, search its docs and check threats
Runs locallyMCP server that audits tool contracts and compatibility for MCP developers
Not checked yetAccess control for AI agents: allow, hold for approval or block each tool call
Runs locallyGuard child_process calls in MCP stdio servers and audit source for shell injection
Runs locallyGives coding agents your repo's engineering standards and checks their changes
Runs locallySecurity checks for Next.js and Supabase apps, run from your AI agent
Not checked yetTurns GuardBee security findings into reviewable fixes your coding agent applies
Runs locallyShared, audited git, test and workflow tools for MCP coding apps that never push
Runs locallyLocal security scanner for AI-written code: SAST, secrets, dependencies and config
Runs locallyMCP server giving AI agents pre-action security checks for code, packages, links
Runs locally
Git guardrail layer that stops coding agents from cutting corners on main branches
Not checked yetThe closest alternatives to Guard are AI Guard, Guard Core, Agent Guardian — MCP Contract Auditor, node9 and MCP stdio ShellGuard.
Yes. AI Guard, Guard Core, node9 have a free or open-source option.