Slide 8 of 28
Part 1 — What Is It?Slide 8
Slide 8 · Why Tools Are the New Attack Surface
MCP changed everything — and the industry hasn't caught up yet
The attack surface for tool misuse just got dramatically larger. Here's why.
What is MCP?

Model Context Protocol (MCP) is an open standard (released by Anthropic in late 2024) that lets AI agents discover and connect to external tools dynamically — at runtime, from any source, without the developer hardcoding them in advance.

Instead of an agent having 5 tools built in, it can now connect to any MCP server and gain access to hundreds of tools — file systems, databases, APIs, calendars, browsers — dynamically.

Why this explodes the ASI02 attack surface

Before MCP: a developer chose which tools to give an agent at build time. The set was fixed, auditable, and small. A security review could enumerate every tool and its permissions.

After MCP: an agent discovers tools at runtime from external registries. The tool set is dynamic, can change between sessions, and the tools come from third parties. Tool descriptor poisoning — where an attacker corrupts the metadata of a legitimate tool — is now possible at scale.

A documented example

In 2025, Invariant Labs demonstrated a prompt injection in GitHub's MCP server where a malicious public repository hid commands in its tool metadata. When the assistant invoked the tool, it exfiltrated private repository data — without the user's knowledge. The tool was legitimate. The misuse was in the metadata.

The new rule of thumb

In an agentic world, every tool your agent can reach — including tools it discovers dynamically — is part of your attack surface. If you haven't audited it, you haven't secured it.

← Back Understood → Show me the two ways this attack plays out