1:1 Mentoring with Big Tech AI Engineers
RAG & MCP

4.3 — Transport Layers: stdio vs SSE vs Streamable HTTP

MCP is transport-agnostic — the protocol is the same regardless of how bytes move. But transport choice has major production implications.

Transport How It Works When to Use Limitations
stdio Client spawns server as subprocess. JSON-RPC over stdin/stdout Local tools (Claude Desktop, VS Code, IDEs). Simplest setup — zero networking Must be local. One client per server process. No auth needed (runs as user)
SSE HTTP POST for client→server, Server-Sent Events for server→client Remote servers, web clients. Backwards-compatible with existing HTTP infra Not truly bidirectional. Server can't initiate requests (only notifications). Session affinity required
Streamable HTTP HTTP POST/GET with streaming responses. Full bidirectional support Production remote deployments. Replaces SSE as the recommended remote transport Newer — less client support. More complex to implement

Transport Decision Tree

Continue Reading

This topic continues with more in-depth content, code examples, and diagrams. Sign up free to unlock the full guide with all 87 sections.

Sign Up Free to Unlock

Free access · No credit card required

More in RAG & MCP

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.

Sign Up Free