MCP: start here.
The Model Context Protocol is how most agents now reach tools. Start with what it is and how authorization works, then read the security post before you connect a server to anything that matters.
Kept current
MCP Changelog Tracker
A living tracker of the Model Context Protocol for engineers who run MCP servers: every specification revision, the latest release of each official SDK, official registry status and notable security advisories, each row sourced and kept current.
Open →Tracker · updated Nov 13, 2026AI Agent Security Incident Log
A dated, sourced log of publicly documented security incidents involving AI agents, coding agents, MCP servers and the AI software supply chain since 2025, split into breaches and CVEs, and kept current as new advisories land.
Open →Read in this order
- What Is MCP (Model Context Protocol)? A Plain-English Guide for 2026
What the Model Context Protocol is and how it works in 2026: hosts, clients and servers, tools, resources and prompts, stdio and Streamable HTTP, every spec version up to the stateless 2026-07-28 release, Linux Foundation governance, adoption, and the real risks.
- MCP Authorization Explained: OAuth 2.1, RFC 9728 and CIMD in 2026
How MCP authorization works in the 2026-07-28 spec: OAuth 2.1 with PKCE, RFC 9728 protected resource metadata, RFC 8707 resource indicators, Client ID Metadata Documents replacing deprecated DCR, the token passthrough ban, and enterprise IdP access through ID-JAG.
- MCP Security in 2026: The Protocol Got Hardened. The Ecosystem Didn't.
A year of MCP CVEs, a rewritten spec, an NSA guidance sheet and an OWASP Top 10 — what actually changed, what didn't, and the six controls I'd insist on before an MCP server touches production.
- Remote vs Local MCP Servers in 2026: stdio vs Streamable HTTP, No Sessions
Remote vs local MCP servers explained for 2026: how stdio and Streamable HTTP work, why HTTP+SSE is deprecated, what the stateless 2026-07-28 spec removed, how Workers, Cloud Run, Lambda, AgentCore and Vercel host MCP, and the auth, scaling and security trade-offs.
- MCP Resources, Prompts, Sampling and Elicitation Explained (2026)
What MCP offers beyond tools under spec 2026-07-28: resources, prompts, elicitation, sampling, roots, the Tasks extension and MCP Apps, which ones are deprecated, how Multi Round-Trip Requests replace server-initiated calls, and which clients support each.
- MCP Tool Design Best Practices (2026): Names, Schemas, Errors, Tokens
How to design MCP tools agents use correctly in 2026: naming rules from the 2026-07-28 spec, tool granularity, the token cost of tool definitions, outputSchema and structuredContent, isError messages, pagination, caching hints and versioning.
- Best MCP Servers for DevOps in 2026: 7 Official Servers, Read-Only First
The official MCP servers worth connecting for DevOps work in late 2026: GitHub, Kubernetes, AWS, Terraform, Grafana, Sentry and Datadog. What each exposes, current versions, how to run them read-only, and the risks to plan for.
- MCP in 2026: 475M SDK Downloads a Month, 39,492 Servers in a Registry Still in Preview, and 12 Gateways Selling the Same 3 Features
The MCP ecosystem ten months after the Linux Foundation took it over, measured from primary sources: 475 million SDK downloads a month across npm and PyPI, three spec revisions ending in the stateless 2026-07-28 rewrite, an official registry I paged to 39,492 servers (24,242 remote) that is still labelled preview while Glama lists 96,340, every major client with different controls, twelve gateways from $0 to $0.005 per thousand calls, the tool-overload numbers (55k tokens before the first prompt, 85 percent recoverable), and a stateless Python server on mcp 2.3.0 that I ran and tested.
Guides and fixes
- How to Build an MCP Server in Python and TypeScript (2026)
- How to Deploy a Secure Remote MCP Server with OAuth (2026)
- How to Deploy a Remote MCP Server on Cloudflare Workers (2026)
- How to Connect MCP Servers to Claude Code, Cursor and VS Code (2026)
- How to Debug an MCP Server with MCP Inspector (2026 Guide)
- How to Run MCP Servers in Docker Securely (2026 Guide)
Latest on MCP
How to Build Agents With Claude Agent SDK Subagents (Python, 2026)
Step-by-step Claude Agent SDK guide pinned to claude-agent-sdk 0.2.176: install, the query loop, custom tools, subagent definitions, permissions and hooks, MCP servers, sessions, budget and depth caps, plus a troubleshooting table for the errors people hit.
11 minOct 20, 2026OWASP Top 10 for LLMs 2026 and Agentic Apps: 20 Risks, Real Incidents
The OWASP Top 10 for LLM Applications 2026 and the Agentic Top 10 explained risk by risk: what moved since 2025, the real incidents behind each entry (EchoLeak, Amazon Q, postmark-mcp, Replit), and the infrastructure controls that contain them.
13 minOct 5, 2026Policy as Code for AI Agents in 2026: Cedar at the Gateway, Rego in the Hook, and the 11.2% the Model Still Lets Through
What actually enforces limits on AI agents in 2026: OPA 1.21 and Rego v1 after the founders moved to Apple, Cedar in Amazon Bedrock AgentCore Policy (GA 3 March 2026, 13 regions, default deny), Kyverno 1.19 retiring ClusterPolicy for CEL, Claude Code hooks that deny even in bypass mode, Codex's Seatbelt and bwrap sandboxes, the MCP 2026-07-28 authorization spec, and why none of it is optional while browser-agent injection success sits at 11.2% and OpenAI says the problem is unlikely to ever be fully solved. With a tested Rego policy and a Cedar policy for tool calls.
13 minSep 9, 2026Agent-to-Agent Protocols in 2026: A2A Reached 1.0, Three ACPs Died or Merged, and MCP Learned to Do Most of the Same Job
What Google's Agent2Agent protocol actually specifies at v1.0, what changed when it moved into the Agentic AI Foundation in August, which vendors have shipped it versus announced it, how MCP's July 2026 revision reproduced A2A's task lifecycle almost state for state, the first real CVE on an A2A surface, what the production data says about how rare multi-hop agent systems are, and a working server and client on the 1.1 SDK with the breaking changes listed.
14 minSep 8, 2026Agent Observability in 2026: The Spans Are Standard, the Standard Isn't Stable, and Nobody Reads the Logs
OpenTelemetry's GenAI conventions moved to their own repo in June and still carry the Development badge; every vendor from Datadog to Grafana ingests them anyway. I instrumented an agent loop with the official Python library, show the exact spans it emits, and go through what the 2026 eval papers say actually catches failures: pass^k, log inspection, and a step budget.
13 minSep 7, 2026Who Is This Agent? Non-Human Identity in 2026, From the RFCs to the Breaches
Machines outnumber humans 109 to 1 in the enterprise directory, the OAuth working group has 70 drafts in flight, MCP just deprecated dynamic registration, and an agent with an over-scoped token deleted a production database in nine seconds. What actually standardised this year, what shipped, and the delegation chain I would build.
16 min