MCP & Agent Protocols
How AI agents connect to tools and to each other: Model Context Protocol servers and spec changes, A2A, WebMCP, and tool and function calling.
Model Context Protocol turned tool integration from a per-framework chore into something an agent can discover at runtime, and it keeps changing underneath the people who build on it. A spec revision can break a working server overnight, and choosing between MCP, A2A and plain function calling decides how much of your integration survives the next one.
These articles track the protocols as they move: what MCP servers are and how agents use them, the breaking changes in each spec release and the errors they produce, where A2A fits, and WebMCP for agents that work inside a browser.
Start here: MCP (glossary) · Tool use (glossary)
What is WebMCP? When and How to Use WebMCP in a Browser Agent?
The decision is per step, not per site: a page can expose a clean search tool and leave its account settings as ordinary DOM controls, so an agent that picks one mode per domain gets the worst of both.
MCP 2026-07-28: 20 Breaking Changes and the Errors They Cause
MCP 2026-07-28 removed sessions, the initialize handshake, and the ability for servers to initiate requests at all. It is wire-incompatible in both directions, so nothing breaks until a client upgrades underneath you. This is the full diff, every error you will hit with the fix for each, the HTTP+SSE deadline that two official sources disagree about, and a scorecard of what the release left alone.
PDF Parsing for AI Agents: The Best MCPs and When to Use Each
Streamline your document workflows by integrating PDF parsing with the Model Context Protocol (MCP). This guide explores how to build a standardized interface that allows AI agents to extract and reason over complex PDF data with precision and ease.
MCP Servers Explained: What They Are and How AI Agents Use Them
Starting as a niche experiment, Model Context Protocol (MCP) is now the universal "USB-C" for AI agent integrations. Let's demystify MCP’s architecture across hosts, clients, and servers and understand how tools, resources, and prompts work together. Essential reading for engineers navigating the massive ecosystem of 18,000+ servers and 97 million monthly downloads.
A2A vs MCP: What Agent Builders Actually Need to Know
MCP and A2A are reshaping AI agent communication. MCP connects agents to tools and data (the toolkit), while A2A enables agents to talk to each other (coordination). They aren't competitors; they are complementary layers of the emerging agentic infrastructure stack essential for complex workflows by 2026.