Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-06-29 · source-backed
The new authorization spec, co-developed by Anthropic, Arcade, Microsoft, and Okta/Auth0, classifies MCP servers as OAuth 2.1 resource servers and standardizes audience binding via Resource Indicators (RFC 8707) and token exchange via RFC 8693. Aembit's writeup explains the choice of delegation over impersonation, so the agent stays distinguishable from the user it acts for. The two-identity model enforces an intersection rule: a compromised agent can only ever do what both the agent and the user are allowed to do. If you're shipping multi-user agents, stop minting broad agent-owned keys and move to on-behalf-of scoped, short-lived tokens per call.
Each link below shares sources, entities, or timing with this story.
If you wrote an MCP server before July, it's on a protocol shape the maintainers have already removed. Not deprecated-with-a-migration-window. Removed from the spec. MCP lead maintainers David Soria Parra and Den Delimarsky published an updated roadmap on August 22, and the re...
The EMA extension lets organizations gate MCP server access through their existing identity provider instead of per-server static credentials. That directly attacks the long-flagged authentication crisis where most MCP auth was static tokens sitting in config. If you run MCP s...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
The Model Context Protocol has a security problem that's no longer theoretical — it's statistical. Between January and February 2026, researchers filed 30+ CVEs against MCP servers, clients, and infrastructure. One package with nearly 500,000 downloads carried a CVSS 9.6 RCE....
For 18 months, Anthropic's Model Context Protocol has been the thing everyone quietly agreed on. You want to plug a tool into an agent, you speak MCP. It won by being early, open, and good enough. That consensus is now contested. Per The Information, Google, Microsoft, Salesfo...
1. Flip your multi-model pipeline to review-then-generate. Instead of using a reasoning model to plan before code generation, let the specialist generate freely and use reasoning tokens for review. Paper shows 90.2% pass@1 vs 87.2% for the planning pattern. Source 2. Audit you...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.