TL;DR
Agent Guard is a Model Context Protocol (MCP) server. Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows. Install with: npx -y @liminallablibs/agent-guard-mcp. Source: https://github.com/liminalpepe/agent-guard-mcp. It speaks the Model Context Protocol and works with any compatible client (Claude, Cursor, Cline, Windsurf, Warp and more).
Agent Guard
Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
Install Command
npx -y @liminallablibs/agent-guard-mcpFrequently Asked Questions
Agent Guard is a Model Context Protocol server that Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
You can install it by running the install command: `npx -y @liminallablibs/agent-guard-mcp`. It then becomes available to any MCP-compatible client such as Claude, Cursor, Cline, Windsurf.
The Agent Guard MCP Server is compatible with any client that speaks the Model Context Protocol — including Claude, Cursor, Cline, Windsurf.
Check the project license on its repository before use.
Reviews
0 reviews· 0.0 average
No reviews yet. Be the first to share your experience.
Leave a review
Rating
Details
- Agent Rank
- 0.0
- License
- Last Updated
- Aug 11, 2026
- Languages
- TypeScript
Client Compatibility
Speaks the Model Context Protocol — works with any compatible client.