How-To

Step-by-step guides for ToolHive and MCP servers

May 22, 2026

MCP Security Best Practices: What Every Enterprise Team Needs to Know in 2026

The Model Context Protocol (MCP) gives AI agents the ability to call real tools: querying databases, writing files, calling APIs, and triggering workflows. That power comes with real security risk. …

May 22, 2026

How to Choose an MCP Gateway

Hand-written Cedar policies won’t scale past a handful of MCP servers. Here’s how Stacklok Enterprise brings RBAC to ToolHive and what it looks like in practice.

May 19, 2026

Stacklok and Anthropic MCP Tunnels: securely connect Claude to everything behind your firewall

You’re invested in Claude, including Claude Code, Claude Cowork, Claude Design. To make it as valuable as possible, you need to connect it to your internal systems and data. Traditionally …

May 11, 2026

MCP server governance starts with discovery

When MCP server URLs live in Slack threads, nobody knows what’s approved. See how Stacklok’s Registry Server solves discovery and access control at scale.

May 07, 2026

Enforcing MCP tool annotation policies with Cedar

MCP tool annotations declare what a tool does. Here’s how to enforce Cedar policies against those declarations using Stacklok’s ToolHive Kubernetes operator.

April 20, 2026

GitHub authorization for MCP servers

It’s easy to justify static credential configuration when an MCP server starts out as a one-user, one-server setup in a developer environment. But things quickly get complicated when that server …