Model Context Protocol

Creator Studio AI assistant shown as a three-tier cake stand, one central pole serving three round plates

Apple Is Adding an AI Chatbot to Pages, Keynote, and Numbers

Apple is adding an AI assistant to Pages, Keynote and Numbers for Apple Creator Studio subscribers. Built on Apple models and OpenAI, it drafts documents, builds slides and works with spreadsheet data, while new Model Context Protocol support on the Mac lets outside AI agents edit files. We explain what it does, what it costs and what businesses should check.

Read more
Gemini Desktop App CustoGoogle Gemini desktop app connecting to custom MCP servers and external AI toolsm MCP Support

Google Expands Custom MCP Support on Gemini Desktop App

Google is continuing to develop its Gemini desktop experience, with custom Model Context Protocol (MCP) server support emerging as another step toward a more connected AI workspace. The reported addition would let users configure external MCP servers through the desktop application’s connector settings, potentially giving Gemini access to a wider range of third-party tools and […]

Read more
ai operating system chesky airbnb agents interview a motherboard with an empty centre socket

Brian Chesky Interview: AI Agents Need Their Own Operating System

Airbnb CEO Brian Chesky told TechCrunch that consumer AI will not work until someone builds a true AI operating system, with a full developer kit that turns every app into an interoperable agent. We explain what he said about Muse, Instinct and ChatGPT’s app store, what such a platform would need, who is closest to building it, and what businesses should prepare now.

Read more
data commons un google global data ai agents a data commons card catalogue cabinet with small drawers

UN Turns to Google to Make Its Global Data Ready for AI Agents

The United Nations has launched the UN System Data Commons at data.un.org, built on Google’s open-source Data Commons platform. It links statistics from across UN agencies, supports plain-language search and lets AI agents fetch official figures through the Model Context Protocol. A UNICEF benchmark of six AI models found average accuracy of just 21.2% on development statistics. We explain how it works, what it fixes and what it means for businesses.

Read more
claude and aws integrations opal late september a keystone wedge block set into the top of a low arch

Claude and AWS: Opal’s Powerful Late-September Integration Launch

Opal Security says Opal Zero reaches general availability at the end of September 2026, and the connector list is the story. It ingests agent identities from Anthropic, AWS Bedrock, OpenAI, Cursor, Okta and Entra, hooks the Claude Compliance API, admin controls for Claude Code and Enterprise-Managed Authorization for MCP connectors, then enforces decisions inside AWS Bedrock AgentCore Gateway and Databricks Unity Gateway rather than adding a proxy of its own. This article covers what the integrations actually do, how Gateway Sync differs from the first generation of agent-security tooling, the Opal Labs research behind the launch, the design partners, the $30,000 launch price and the gaps worth watching.

Read more
google home mcp ai agents smart home a doorbell push unit with round button

Google Will Now Let Any AI Agent Run Your Smart Home

Google began rolling out early access to Home MCP on 16 September 2026, a Model Context Protocol server that lets any MCP-capable AI agent enumerate devices, read live state, search event history and execute actions across the Google Home ecosystem. Google named Antigravity, Claude, ChatGPT, Hermes and OpenClaw. Access is limited to Google Home Premium Advanced subscribers in the US at $20 a month, setup requires a Google Cloud project with the Home APIs enabled, and the server enforces rate limits plus a block on sensitive actions such as unlocking doors.

Read more
gemini business custom mcp server connections a arch bridge span on two piers

Google Gemini Business Adds Support for Custom MCP Server Connections

Google has extended Gemini Enterprise – Business edition so a team administrator can register a custom MCP server connection and hand Gemini a callable interface to systems Google will never build a connector for. This is a documentation-first walkthrough of what that actually involves: the Connected apps path versus the Google Cloud data store path, the four hard requirements that disqualify most existing internal tooling on day one (StreamableHTTP transport, a publicly trusted TLS certificate, a public HTTPS endpoint and a publicly reachable identity provider), the OAuth field-by-field configuration, the 100-enabled-actions cap, the project-level quotas, the Pre-GA status caveat, and the security exposure a public MCP endpoint creates.

Read more
CHAT