Path 3 of 6Practitioner6 lessons · 55 minReviewed 2026-11-10
Agents, tools and MCP
Design agent tools and identities so a steered agent can do little harm, review MCP servers and their authorization like any other third-party code, and put approvals and logs where they change outcomes.
For: AppSec engineers, platform teams and reviewers approving agents and MCP servers
- 01 Tool misuse and excessive agency: design tools narrowly
Treat an agent's tools as its permissions, recognise the three root causes of excessive agency, and design tools that code can validate and scope.
9 min · 4 questions
- 02 Agent identity and least privilege
Choose how an agent authenticates, keep the end user visible in every action, and manage agent credentials as non-human identities with narrow, short-lived scope.
9 min · 4 questions
- 03 How MCP works, and how MCP servers go wrong
Understand the MCP host, client and server roles, then recognise tool poisoning, shadowing, rug pulls, malicious servers and vulnerable bridges, and the controls that contain them.
10 min · 4 questions
- 04 MCP authorization: audience-bound tokens and the attacks around them
Read the MCP authorization model as a reviewer: who issues which token for whom, why token passthrough is forbidden, and which OAuth attacks the security best practices tell clients and servers to block.
10 min · 4 questions
- 05 Approval gates that hold up: fatigue, bypass and what to gate
Place human approvals where they change outcomes, make each approval specific and unforgeable, and stop agents from switching their own approvals off.
9 min · 4 questions
- 06 Logging and auditing agents
Record enough about each agent step to reconstruct an incident, use the OpenTelemetry GenAI conventions instead of inventing a schema, and decide deliberately how much content to capture.
8 min · 4 questions
Lessons cite primary sources and were last checked on the date shown in each lesson. Corrections are welcome by email (footer). Other paths: Fundamentals · LLM applications · AI coding assistants · Red teaming · Detect & respond