Skip to main content

Overview

The MintMCP LLM Gateway is a lightweight service that sits between your LLM client (e.g. Cursor or Claude Code) and the model itself, forwarding and monitoring requests. It provides observability into how employees are using LLM clients, including what tools the LLMs are invoking. With this visibility, you can detect risky behavior and apply rules to block dangerous actions before the client runs them.

LLM Gateway DashboardLLM Gateway Activity

Security Considerations​

Coding agents operate with extensive system access - reading files, executing commands, and accessing production systems through MCP tools. Without monitoring, organizations cannot see what agents access or control their actions. The LLM Gateway provides essential visibility and control over agent behavior. See Security for detailed security considerations.