CyberCage

Security platform for AI tools and MCP servers

6 followers

Security platform for AI tools and MCP servers

6 followers

We built CyberCage to manage MCP servers and AI tool traffic across teams. Who's running what? What data is going where? MCP Management — Auto-discovery, approval workflows, org-wide control down to individual tools. Integrates with GitHub's MCP Catalog. Works with Claude Code, Cursor, VS Code, Windsurf, IntelliJ, n8n, and more. In beta: On-device network agent, PII detection, content inspection. Coming soon: BYOLLM, browser extensions. P.S. Open-sourcing CyberSmol v1.0 soon ♥

Free Options

Launch tags:Artificial Intelligence•Security

Launch Team

Flowstep — Generate real UI in seconds

Generate real UI in seconds

Promoted

Hunter

📌

We've been building with AI tools and noticed there wasn't a good way to manage MCP servers across a team or see what's actually flowing to LLM providers. Who's running what? Which tools are approved? What data is going where or whats shared on AI websites? Here is the full list of supported AI Assistants and IDEs: - Claude Desktop - Claude Code - VS Code - Cursor - Windsurf - Zed - Kiro - Codex CLI - Antigravity - IntelliJ IDEA, and n8n — https://www.npmjs.com/package/@c.... More: https://docs.cybercage.io/

Report

2mo ago

This is a much-needed layer of governance for the AI-augmented workflow. The auto-discovery of MCP servers is a killer feature.

A practical question for teams: Does the approval workflow allow for different policies per environment? For example, can a developer freely experiment with MCP servers in a local/dev setting, but have them blocked or require approval before they can be used in a production CI/CD pipeline?

Report

2mo ago