MCP security, explained

Blog

Guides and deep-dives on MCP security — tool poisoning, toxic flows, supply-chain risk and how to scan a Model Context Protocol server before you connect it to your data.

July 21, 2026

Introducing the MCP Trust Checker API: Scan Any MCP Server Over HTTP

A beginner-friendly guide to the new free MCP Trust Checker API: what it does, how to get a key, and how to scan any MCP server over a single HTTPS request — with copy-paste examples you can run in two minutes.

Read more →
July 20, 2026

MCP Security: The Complete 2026 Guide

A complete 2026 guide to MCP security: why tool descriptions are a new attack surface, the six main risk categories, and how to actually check a server before you trust it.

Read more →
July 17, 2026

How to Scan an MCP Server: Free Step-by-Step Guide

A step-by-step guide to scanning any MCP server for prompt injection, tool poisoning, and supply-chain risk with one free npx command — no signup required.

Read more →
July 14, 2026

MCP Tool Poisoning: Hidden Instructions That Hijack Agents

How hidden instructions in MCP tool descriptions hijack AI agents — the five attack shapes defenders should recognize, why "looks clean" is not clean, and how to detect poisoning deterministically.

Read more →
July 11, 2026

The Lethal Trifecta: How MCP Toxic Flows Exfiltrate Data

How the lethal trifecta assembles itself from benign MCP tools, why single-tool scanners miss cross-tool composition, and how a static toxic-flow graph proves the exfiltration primitive before an attacker uses it.

Read more →
July 8, 2026

MCP Rug Pulls: Supply-Chain Security for MCP Servers

How to vet npm and PyPI MCP servers before you install them — and how hash-pinning the tool surface and the artifact bytes catches a rug pull, even a same-version republish.

Read more →
June 10, 2026

MCP Servers Explained: Tools, Resources, and Prompts

An MCP server exposes exactly three primitives — tools, resources, and prompts. Here is what each one does, how the client and model use them, how capability negotiation works at connect time, and why tool descriptions are a security concern.

Read more →
June 8, 2026

MCP vs API and Function Calling: When to Standardize on the Model Context Protocol

A clear-eyed comparison of MCP vs API and plain function calling: what MCP standardizes, the M×N to M+N argument, when a direct API call is simpler, and the new trust surface a reusable server introduces.

Read more →
June 6, 2026

How to Add an MCP Server to Claude: A Step-by-Step Setup Guide

A practical, client-agnostic walkthrough for connecting an MCP server to Claude Desktop or Claude Code: config file locations, the exact mcpServers JSON for stdio and HTTP transports, restart-and-verify steps, and the common gotchas that make a server fail to show up.

Read more →
June 4, 2026

How to Build an MCP Server: A Practical Tutorial for Developers

A practical, developer-focused tutorial on how to build an MCP server: choosing a transport, declaring tools, resources, and prompts, a minimal TypeScript SDK sketch, why model-facing descriptions are an injection surface, and how to test and safely publish.

Read more →
June 2, 2026

What Is the Model Context Protocol (MCP)? A Developer's Guide

A clear, beginner-friendly-but-technical explainer of the Model Context Protocol: what MCP is, why it exists, how its client–server architecture works, what a server exposes, the two transports, and where you'll meet it in 2026.

Read more →