GoKawiil
Tech News
Vespper, a Y Combinator F24 startup, has launched a Model Context Protocol (MCP) server aimed at letting AI agents reliably read and edit .docx files. The company says existing approaches—raw OOXML SDKs, opinionated MCP tools, or lossy Markdown/HTML round-tripping—break down on complex real-world Word documents used in legal, finance, and healthcare workflows.
Startup Ando exited stealth Thursday with a messaging platform positioned as an alternative to Slack, giving AI agents their own identities and inboxes so they can join channels, DMs and calls alongside human coworkers. Founder Sara Du said the app lets agents browse and join conversations, contribute to ongoing work, and message humans directly when needed, without a person relaying information between the agent and the team.
A developer has released ForensicDbg, a post-mortem debugging tool for native Windows x64/x86 crashes, now in private beta. The tool exposes its debugging engine to AI systems via an MCP server, aiming to improve AI-assisted crash analysis while reducing token usage. As an example bug, the release notes describe a null-pointer dereference in CTextWindowBase::SetSelectionBegin that occurs when a disassembly panel is clicked before any code lines are loaded.
Foremerge is a new open-source coordination protocol that sits on top of Git to let multiple AI coding agents, such as Claude Code, Codex, or Cursor, share their intended changes before writing code. Each agent registers what function or component it plans to modify in a shared SQLite-backed list stored inside the project's .git folder, so overlapping or contradictory plans can be flagged before they merge. The current release, version 0.5.0, is a local-first, pre-1.0 MVP with a working CLI, JSON API, MCP server, and conflict detector, though it doesn't yet support coordination across multiple machines.
A developer who attended an MCP-focused industry event says the Model Context Protocol, released by Anthropic in November 2024 and later handed to the Linux Foundation's Agentic AI Foundation, was designed for weaker, less agentic models than exist today. As adoption exploded, users began overloading context windows by connecting many MCP servers at once, prompting platforms like Composio, MintMCP, and Pipedream to build workaround tools that centralize credentials and trim tool lists.
Apple's WebKit blog detailed Safari 27.0's developer features, headlined by a new Safari MCP server that lets AI coding agents like Claude Code or Codex control the browser to inspect DOM elements, network requests, screenshots, and console output. Developers enable it through Safari's Developer settings after turning on features for web developers, and Apple says the server runs locally without sending data externally.
Scry is a new search-over-the-web service built for AI agents, exposed through the Model Context Protocol as well as a direct HTTP API. Developers connect tools like Claude Code, Codex, or Cursor to a single MCP endpoint, authenticate via OAuth or an API key, and query a rolling crawl of high-information web pages using a SQL-like interface. The service also introduces congestion-based pricing tied to usage load.
Flet has launched its 1.0 release, providing developers a complete framework to build, test, and ship Python applications across desktop, mobile, and web. The release includes over 150 UI controls, prebuilt Python packages for iOS and Android, browser support via Pyodide/WebAssembly, and tools like flet build for packaging apps for app stores.
Ax-check.com is a new tool that runs three AI agents through a company's onboarding flow to see how far they get before failing or succeeding. It then produces specific recommendations for fixing documentation, marketing pages, CLI tools, MCP configurations, or Skills that block agent access.
Hister is a new privacy-focused search tool that indexes the full text of web pages visited and local files kept on a user's machine. It runs locally through a browser extension, terminal, or web interface, and can also be accessed by AI assistants via MCP integration. The tool is available as a downloadable binary or through Homebrew, Docker, and Nix.
Google is adding a Model Context Protocol connector to Google Home, opening the smart home platform to AI assistants beyond its own Gemini. The rollout is starting with a limited group of testers rather than all users at once.
Google Home will integrate the Model Context Protocol, letting agents like Claude, Hermes, Open Claw and Google's own Antigravity connect to a user's devices and event history through natural language commands. The feature will roll out as early access in the coming weeks, but only for subscribers paying $20 a month or $200 a year for Google Home Premium Advanced.