RAG & MCP

MCP Discovery

MCP tool discovery and capability negotiation: how clients discover server capabilities and tools dynamically.

Last updated 2026-06-11

4.4 — How the LLM Discovers and Selects MCP Tools

This is the most common interview question about MCP: "How does the model know which tool to use?" The answer involves three stages.

Stage 1: Discovery — tools/list at Connection Time

Stage 2: Schema Injection — Tools Become Part of the Prompt

The MCP client (Claude Desktop, your app) takes every discovered tool schema and injects them into the API call to the LLM. Here's what the LLM actually sees in its system prompt:

RAG Architecture

Preview

Retrieval-Augmented Generation (RAG) architecture explained: ingestion pipeline, vector search, prompt augmentation, and production patterns.

Document Processing

Preview

Document processing for RAG pipelines: PDF parsing, OCR, table extraction, and multi-modal document understanding.

Chunking Strategies

Preview

Text chunking strategies for RAG: fixed-size, semantic, recursive, and document-aware chunking with performance comparisons.

Embedding & Indexing

Preview

Embedding models and vector indexing for RAG: choosing embeddings, HNSW vs IVF, dimensionality, and index optimization.

Get full access to all 87+ sections with code examples, diagrams, and interactive animations.

Unlock Premium

4.4 — How the LLM Discovers and Selects MCP Tools

Stage 1: Discovery — tools/list at Connection Time

Stage 2: Schema Injection — Tools Become Part of the Prompt

More in RAG & MCP

RAG Architecture

Document Processing

Chunking Strategies

Embedding & Indexing