# Model Context Protocol (MCP) Security: How to Restrict Tool Access Using AI Gateways

For too long, the Model Context Protocol (MCP) has operated on a principle of open access: connect an AI agent to an MCP server, and it gets access to every single tool that server offers. While this approach is simple for initial experimentation, it quickly becomes a liability in production.…
[](/blog/engineering/mcp-tool-governance-security-meets-context-efficiency)












