Skip to content

Guides ​

Each guide answers one question end to end, with L2M as the worked example: what the technique is and when you need it, a walkthrough with real settings and commands, how it works, and what it does not do. Everything runs on your own deployment.

GuideWhen you need it
Run a self-hosted MCP gatewaySeveral people or agents call the same MCP servers, and you want one endpoint, per-client tokens and one place to switch a tool off.
Govern MCP toolsMCP servers offer tools that change things, and different roles should get different tools.
Least privilege from real runsYou want rules that give each agent only the tools it really uses, checked against recorded calls before they apply.
Test MCP servers in CIServers change their schemas or go down, and you want tests that don't depend on them and a build that fails on breaking changes.
CI for AI agentsPrompt, model and tool changes should be regression-tested and gated before they reach production.
Human approval for agent tool callsAn agent's write-tool calls should wait for a person, with the decision on record.

New to L2M? Start with Build your first MCP agent, or look around the live demo first.

This website (not the L2M product) uses Google Analytics, only after you accept cookies. Cookie settings