Skip to lesson
Exit
AI & Agent Security Threat Model1 / 4

1 min lesson

MCP & model-context security

Tell someone how to act on this idea: "Each server you connect is a new mouth feeding the model context and a new hand the model can use."

Step 1 of 4

MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition. - the Model Context Protocol - lets an agent connect to external tools and data sources through a standard interface. Each server you connect is a new mouth feeding the model context and a new hand the model can use. Each one is a trust boundary.

MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition. is genuinely useful and genuinely dangerous, which is why it earns its own round-worthy discussion. A connected server returns content the model treats as context and exposes tools the model can call. If you don't control that server, you've extended the lethal trifecta to a third party.

Learn more

Advanced table

Reference table

Risk
Instruction injection
Mechanism
Server returns content laced with imperatives the model obeys
What it enables
A malicious or compromised server hijacks the agent mid-task - indirect prompt injection over MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition.
Risk
Context exfiltration
Mechanism
Server's tool accepts arguments the model fills from its context
What it enables
The model passes secrets, code or file contents into a tool call that ships them to the server
Risk
Tool shadowing / confused deputy
Mechanism
A server's tool name or description impersonates a trusted one
What it enables
The agent calls the attacker's tool thinking it's the safe one, with the user's authority

A compromised MCP server can inject instructions inbound, exfiltrate context outbound and impersonate a tool the agent already trusts.

Learn more

Optional practice

Practice: MCP & model-context security