Latest blog posts

This week in MCP: Slack’s agent-native servers, Google’s Managed MCP for Spanner, Cloud SQL and more, Gemini 3.1 Pro and Deep Think, Claude Sonnet 4.6, Microsoft’s Security Dashboard for AI, plus new infra funding.

This week’s MCP Weekly: EU probes Meta’s WhatsApp AI lockout, OpenAI ships Frontier and tests ChatGPT ads, Anthropic launches Claude Opus 4.6, plus hosted MCP.

From Xcode to Snowflake, agents are going first-party. This week's digest breaks down Codex on Mac, GitHub Agent HQ, OpenAI’s $200M Snowflake partnership, and why Moltbook put agent security back in the spotlight.

This MCP Weekly covers Anthropic’s new Claude constitution and MCP tool integrations, GitHub’s Copilot SDK technical preview, OpenAI’s Prism and Codex agent loop details, plus a fresh $30B SoftBank move around OpenAI.

This week's digest: ChatGPT Go goes global, OpenAI taps Cerebras for 750MW inference, and MCP spreads across Azure Functions, Salesforce, AWS, and Google Cloud.

MCP Weekly kicks off 2026 with a look at the ways the agentic shift is reshaping AI, from UCP’s launch and MCP storefronts to desktop coworkers and the rise of execution-first infrastructure.

A 2025 retrospective into the agentic shift: MCP and AAIF standards, massive AI infrastructure spend, enterprise agents in production, and the new rules shaping autonomous systems.

This MCP Weekly covers Anthropic’s Genesis Mission with the U.S. Department of Energy, new Agent Skills and GPT-5.2 Codex advances, plus a critical Cursor MCP RCE that exposes rising agent security risks.

This MCP Weekly tracks Copilot’s shift into agentic AI, the security reality of production agents, and MCP’s move from backend plumbing into the UI layer.

This MCP Weekly covers MCP’s move to the Linux Foundation, rising support from AWS and Google Cloud, and new security focused MCP servers for production use.

A major week for MCP as AWS unifies cloud architecture, security platforms emerge to protect agent actions, and Snowflake and Anthropic commit $200M to governed AI agents.

This week: MCP turns one as OpenAI’s supply-chain breach underscores rising security demands and major vendors adopt MCP for payments, infrastructure, and long-running agents.

This week: Power BI’s server debut, evolving agent frameworks, and expanding enterprise-grade security and tooling. Plus: lessons from the Cloudflare outage.

This week: Agent Sandbox, an MCP powered cyber espionage case, D365 ERP, Context Forge and new GPT 5.1 tools show MCP becoming core enterprise infrastructure.