Model Context Protocol (MCP)
The open standard (launched November 2024) that lets AI agents call external systems through typed tools: the USB port between models like Claude and the software that does things.
MCP lets an assistant discover and call tools exposed by a server. LinkedBoost uses it for workspace and LinkedIn operations. What a call changes, when it executes, and what requires review remain properties of the server and the connected workflow.
In practice
Connect the assistant to LinkedBoost, inspect available tools, and start with a read of the workspace before requesting an action.
What to check
The protocol standardizes communication, not the provider's business rules or human approval. Available operations depend on the connected server.
Use it in LinkedBoost
- get_workspace_overview
Orient yourself in a workspace or inspect locally staged search rows.
- list_agent_activity
Review the workspace's recorded tool calls across MCP, CLI, and HTTP.
Related terms
- Agent-native
- Software designed to be operated by an AI agent through typed tools, rather than by a human through a dashboard: the interface is the protocol, not the UI.
- Envelope response
- A consistent structured reply shape from every tool call: success flag, data, a one-line summary, notable signals, and durable learnings: so an agent always knows what happened and what deserves attention.