MCP Trust Pack: a security layer for MCP tool calls

<p>Most API documentation is written for humans.</p> <p>MCP tool descriptions are different.</p> <p>They are read by the model that decides what to call next.</p> <p>That means

<h2> The Setup </h2> <p>MCP (Model Context Protocol) lets AI agents call external tools. Instead of just reading files and running bash, the agent gets structured access to APIs,

<blockquote> <p>Disclosure: I'm the author of <a href="https://github.com/razukc/capgate" rel="noopener noreferrer">capgate</a>, a compile-time policy compiler for MCP servers.

<h1>MCP Protocol Deep-Dive: How Tool Discovery Actually Works</h1> <p>Unlock the mechanics of the Model Context Protocol. We dissect the JSON-RPC handshake that enables dynamic

<p>The AI world has a plumbing problem. We have incredible language models, but connecting them to real tools — databases, APIs, file systems, other agents — still feels like