Microsoft Foundry Blog · Oct 20, 2026 · 12:22 AM

Microsoft Foundry's browser automation tool goes GA, with Live View, take control, and an MCP endpoint

Foundry agents now get a managed cloud browser (via Playwright Workspaces, provisioned as a separate Azure resource) that can reach public sites and private VNet apps, exposed to prompt or hosted agents through a toolbox's MCP-compatible endpoint. Operators can watch sessions live, take over mid-run, and require approval before clicks, typing, or uploads, which you enable only when a task needs them.

Read at devblogs.microsoft.com

More news

View all

Report: Anthropic, Google (Gemini 4 Carbon), and OpenAI (a cheaper Terra model) all have new models in the pipeline

Per The Information, Anthropic is testing a model that infers your real goal from thin instructions (one tester says it traces a single bug to the broader problem and offers a fuller fix), Google is readying Gemini 4 Carbon above last week's Argon, and OpenAI may ship a new Terra model within weeks that beats GPT 6.1 Sol on price. None of it is announced yet, so treat names and timing as unconfirmed…

Investing.com (citing The Information) 29 minutes ago

OpenAI says GPT-6 Astra now builds a SQLite clone in COBOL, OCaml, and Fortran, not just Python

On OpenAI's new MultiLangBench, where a model builds a SQLite compatible engine in 20 languages, GPT 6 Astra averages an 87.4% test pass rate (COBOL jumps from 10.9% to 72.1%) versus 26.8% for GPT 5.6 Sol. On its COBOL migration eval, GPT 6.1 Sol hits 86.6% at low reasoning effort and 97.9% at high, though both benchmarks are OpenAI's own and not independently verified yet…

OpenAI 2 hours ago

Neural Concept's MCP Bridge lets AI agents drive CATIA, NX, ANSA, HyperMesh, and Abaqus

Built on MCP, the connectors let an agent carry engineering work from CAD (CATIA, NX) through meshing (ANSA, HyperMesh) to simulation (Abaqus) across Windows workstations and Linux clusters, with engineers setting goals and validating results; one customer cut a wheel rim geometry cleanup from a day to about three minutes. It's available now, but only to existing Neural Concept customers (SiliconANGLE)…

Neural Concept 3 hours ago

Official MCP reference servers hit v2.0.0 on the 2026-07-28 spec, and now need Node 24

The filesystem, memory, sequential thinking, and everything servers move to TypeScript SDK v2 and the 2026 07 28 spec while still answering older clients, and the Python fetch, git, and time servers ( 2026.10.19 ) now return a JSON RPC 32602 error for unknown tools instead of an isError result. The TypeScript servers require Node 24 or later, and v1.0.0 (Oct 11) was the final legacy era release, so pin it if you can't upgrade yet…

GitHub (modelcontextprotocol/servers) 5 hours ago

Wodby Agent adds built-in coding and ops chats to Wodby, running on GLM 5.3 with shared AI credits

Workspace chats can edit the dev checkout, run commands, and read service logs (asking before Git pushes by default, with optional approvals for shell, web, and platform changes), while organization chats propose stacks, flag EOL service versions, and dig into failed deploys. It bills against one time org AI credits ($5 on the Developer plan, $10 with a paid subscription), and Wodby also opened the same dev workspaces to Codex and Claude Code (docs)…

Wodby Blog 6 hours ago

Spotted something we missed? Start a thread.