What is MCP (Model Context Protocol)?
An open protocol that lets AI applications (like IDE assistants) connect to external tools and data sources through a standard JSON-RPC interface.
AI assistants are only as good as the context they can reach. MCP standardizes how an assistant discovers and calls external capabilities — a server declares tools (functions with schemas), and any MCP-compatible client can call them, no bespoke integration per pairing.
The practical impact for documentation is large: instead of an IDE assistant answering API questions from training data frozen months ago, it can call an MCP server that searches the vendor's live docs and answer from current content.
Because MCP is an open standard, one server serves every compatible client — Cursor, Claude, and the growing ecosystem — from a single endpoint.
How BeforeQuery uses this
Every BeforeQuery knowledge base exposes an MCP server at /mcp/knowledge-bases/:id with three tools — search_docs, ask_question, and list_sources — authenticated by client keys and recorded in traces. Developers get your current docs inside their editor, not stale training data.
Related terms
A2A (Agent-to-Agent)
A protocol for AI agents to discover and communicate with each other, exchanging messages through published capability descriptions called AgentCards.
RAG (Retrieval-Augmented Generation)
An AI architecture that retrieves relevant documents from a trusted knowledge source and passes them to a language model, so answers are grounded in real content instead of the model's training data.
Knowledge Base
A curated, indexed collection of an organization's knowledge — docs, wikis, tickets, repos — that an AI assistant retrieves from when answering questions.
From definition to deployment
Connect a knowledge source and see cited AI answers on your own content in minutes — free, no credit card required.
Get Started Free