Tool registration
The handshake in which a server tells the host what tools it offers, and the host puts those names, descriptions and schemas into the model's context. It is a security event, not plumbing: the descriptions are attacker-controllable text that enters the context with implicit trust, before any user input, and they are re-read on every session. This is the window tool poisoning and shadowing exploit.
See also tool poisoning · capability expansion · MCP
Related terms
-
Tool poisoning
Attack concepts
Hiding instructions in the metadata an agent reads to learn how to use a tool — an MCP server's tool description, its parameter documentation, its schema…
-
Capability expansion
Attack concepts
A tool or server that was reviewed and approved in one form quietly acquires new powers later — a new parameter, a new network destination, a new…
-
MCP
Agents & architecture
An open protocol, introduced by Anthropic in 2024 and now broadly adopted, that standardises how agents connect to external tools and data sources.
Agents & architecture
Where the attacks above actually land. The vocabulary here is worth precision, because the difference between "the model decided" and "the tool ran" is the difference between a risk and an incident.