You added an MCP server to your AI assistant. Did you check what it can touch?

<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,

<p>In January and February 2026, security researchers filed <a href="https://www.heyuan110.com/posts/ai/2026-03-10-mcp-security-2026/" rel="noopener noreferrer">30 CVEs against

<p>Most MCP tutorials stop at a single stdio tool. These notes cover what I had to change once a server of mine had actual users, in the order the problems appeared.</p> <h2>

<h2> The Problem </h2> <p>The MCP ecosystem is expanding at an extraordinary pace. Anthropic, Microsoft, Google, AWS, and Cloudflare are all publishing official MCP servers.

<p><a class="article-body-image-wrapper"

<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

<p>MCP feels easy until it isn't. The first time you wire up a stdio server and call a tool from a Claude Agent SDK loop, the whole thing fits on a slide. Then you put it in front

<p><em>Part 6 of the MCP in Practice Series · Back: <a href="https://dev.to/gursharansingh/build-your-first-mcp-server-and-client-bhh">Part 5 — Build Your First MCP Server (and