MCP

The more an agent can do, the more a platform team has to think about what it should be allowed to do. That's a governance problem that usually gets solved by restricting access. GitLab 19.4 introduces a solution. New MCP server tools let any agent run pipelines, open MRs, and triage vulnerabilities in GitLab, governed by the same rules for every agent, internal or third-party. Now in beta. Read the blog to learn more.

• about.gitlab.com

Agents browsing your site can use WebMCP tools instead of clicking through your UI. 𝚖𝚌𝚙-𝚑𝚊𝚗𝚍𝚕𝚎𝚛 𝟸.𝟸.𝟶 adds experimental WebMCP support. Allowlist tools and add one script tag. In-browser agents call them as the signed-in user, with no OAuth flow.

• vercel.com

随便跑来源不明的 Agent Skill 和 MCP 配置，等同于在本地裸奔。如何在安装前，安全审查它们有没有偷走凭据？ 开源新工具 jev-security-scan 提供了「零执行」的审查方案。它结合本地静态检查与 TypeSafe Jev，在不启动服务、不安装依赖的情况下，提前扫出代码里的隐蔽行为。 主要特性： • 拒绝“下载即中招”：只读取目标文本、配置和脚本，完全不执行目标代码，从根本上防止触发恶意安装钩子。 • 精准抓取证据：若发现窃取 SSH 私钥、提示词注入或越权外传，会直接输出具体文件、行号与脱敏后的代码段。 • 极简无依赖：仅依赖 Python 3.10+ 标准库，连 pip install 都省了，天然支持作为 Codex 或 Claude Code 的 Skill 直接调用。 • 双模式切换：高敏感项目可使用 local 纯离线静态检查；常规项目开启 jev 模式进行深度语义分析。 对于经常折腾各种开源 Agent 扩展的开发者，在运行新框架前，用它过一遍“X光”是非常实用的防线。

• github.com

Omnara is now available over MCP MCP joins the @omnaraai API, SDK, and CLI. Connect Claude Code, Codex, Cursor, or any MCP client and spin up production-grade agents

10 prompts to try in the new TradingView MCP inside Claude. Most people missed this, but TV just launched its official Claude MCP. I posted about how to set it up (on my profile). Once you get things connected, here are 10 useful prompts to test:

AI Agent 写代码越来越快，代码评审反而成了新的瓶颈。 过去，一个 Pull Request 通常对应开发者几小时甚至几天的工作。现在 Agent 可以一次改几十个文件，但评审者最后看到的，往往只有一份巨大的代码差异，很难知道这些修改是在什么要求下产生，又经过了哪些尝试。 Zed 新开放公测的 Delta，想把这部分过程重新补回来。它会把 Agent 对话、每一次代码修改和后续评论放进同一份历史里。看到一段有问题的代码，可以直接往前追，看看当时提了什么需求，Agent 又是怎么一步步改到这里。 评审也不再等到开发结束才开始。开发者可以随时另开一个线程，让人或另一个 Agent 检查当前代码，并在独立副本里继续修改。 Zed 已经先在自己身上试了。Delta 仓库关闭了 GitHub Pull Request，33 名成员已经通过 Delta 向主分支合入 570 次改动。 Git 仍然保留，commit、push 和构建流程都不受影响。Zed 真正想改的是代码评审这一层：当越来越多代码由 Agent 生成，只看最终 diff，可能已经不够了。 Delta 目前支持 macOS、Linux、Windows 和网页端，公测期间免费。MCP 和远程运行环境等功能还在开发。

@zeddotdev

Delta is now in public beta. It’s a multiplayer environment for coding with agents and reviewing what they build, with every code change linked to the conversation that produced it. > Anyone can download it today on macOS, Linux, and Windows:

• delta.dev

One AI agent with too much access can undo years of security work in a single afternoon. The risk grows fast, because 100 humans need 100 access decisions while a fleet of agents needs a million. Opal Zero just solved it with just-in-time access that gives each agent exactly what it needs and nothing more, zero standing permissions, zero human toil, zero friction.

@howardting

You want your AI agents to run fast. But as you scale, managing their permissions turns into a million micro-decisions. > Introducing Opal Zero. The end-to-end access governance platform purpose-built for AI agents. > How it works: AI-driven contextual decisions, evaluating intent, ownership, and purpose > Dynamic, just-in-time access (scoped to exactly what the agent needs). Enforces security decisions across your existing MCP gateways > 0 standing permissions, 0 human toil, 0 friction > Let your agents run, safely.

zod 4.5 shipped `z.compile()` some days back. ~10x faster schema parsing on objects/arrays which is a real performance win. i asked claude to optimize hot zod paths today but it was totally confused what to do. Did not even realise that something interesting shipped since this isn’t in any models training data yet. Spent 2 minutes connecting liner's search mcp (oauth once), asked again. it pulled the current zod blog + compile guide, with sources, and rewrote it correctly. “can it code” - yes, but “is it stuck on last year’s packages” - also yes. check out liner search mcp (50 searches/day free) and works everywhere mcp works

@search_liner

Liner's Search MCP is now live. Your agent now answers using only the latest data, with sources attached. 200 free searches a day, and the first 1,000 connected accounts keep it for a year. > No API key. One OAuth click and you're connected ↓

• hey.liner.com

SpaceX AI engineer Lauren Tan just released a Grok Bot template that turns APIs into working Cursor plugins by defining the data shape, building the smallest scaffold and proving it locally, collapsing the whole workflow into API to Grok Bot to MCP and skills to working plugin. → Handles the full workflow from API definition to working Cursor plugin automatically → "Open your laptop once a day" once the template is running → SpaceX AI just turned building agent plugins into a repeatable workflow

很多 AI 助手原型，一遇到多人协作就开始补基础设施。 Octop 把这些能力做成可自托管的多用户、多 Agent 控制台：可以创建与管理 Agent，连接 OAuth 应用和 MCP 网关，配置 IM 渠道、可视化定时任务、知识库、插件及外部编码 Agent。默认使用 SQLite，也可切换 PostgreSQL；聊天、工作区和凭据保存在本机目录。 它还提供 JWT 用户隔离、PII 脱敏、工具审批与可编辑的 shell 命令规则，降低共享环境中的误操作风险。模型、存储和渠道都可替换，适合想把零散 Agent 原型整理成内部服务，又希望保留部署控制权的团队。

• github.com

Grok Build just got another strong workflow upgrade, especially for people running more background work and multi-agent tasks. Background shell commands now show up as live task rows with streaming output, so you can actually watch what’s happening instead of treating background work like a black box. There’s also a new dashboard preview toggle, plus stronger organization controls for restricting unmanaged hooks. On the reliability side, folder trust in sandbox mode is fixed, pinned agents stay put, config-defined agents are respected properly, MCP plugin authentication is more reliable, and background subagent approval requests now surface instead of silently failing Release Notes: v1.0.36 Features: • New Dashboard preview setting lets you hide the selected-session preview panel on the dashboard. • New policy setting allows organizations to disable hooks that are not from managed policy. • Background shell commands now appear as live task rows with streaming output. Bug Fixes: • grok --sandbox no longer

Starting today, you can connect multiple accounts with most plugins in ChatGPT! 🎉 Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin directory: Devs: this works automatically, with no changes needed. But, to make the experience for users of your plugin even better, add a profile tool to your MCP server so ChatGPT can label the accounts:

• chatgpt.com
• developers.openai.com

CLAUDE CODE, CURSOR AND CODEX CAN NOW LICENSE A DATASET OVER MCP, IN THE MIDDLE OF A TASK • @LuelCompany Data Platform > Your agent browses and licenses rights-cleared datasets directly, with no procurement thread: > It speaks MCP, so any MCP client reaches the same catalog the same way. > Every set clears Luel's QA pipeline before it ever appears in that catalog. • the other half of the marketplace > Anyone sitting on a dataset can submit and sell it through the same workflow and the same QA. > The catalog opens with their most requested sets and keeps updating. > 850,000 contributors across the network are what makes that coverage exist at all. Buying data used to mean a licensing review and a sample that lands weeks later -> now it is a tool call inside the task you were already running. The first data marketplace where the buyer is the agent ↓

@LuelCompany

The Luel data marketplace is becoming agent-native. > Buying data is still one of the s

• luel.ai

🚀 Codex CLI 0.155.0 is out! 🎙 Experimental /voice with live transcripts and mic controls 🧠 Live reasoning summaries and turn timestamps in status row 🔐 Touch ID for MCP requests on Mac Changelog:

• github.com

Grok Build just got another strong performance + reliability upgrade MCP connections now report their real handshake state more accurately, tool searches and calls show much more detail on the daemon path, and /memory gets a much better experience with content search, copy confirmations, faster deletes, and proper support on narrow terminals The biggest performance win is under the hood: syntax highlighting now uses far less memory and runs faster on large TypeScript and other files Release Notes: v1.0.35 Bug Fixes: • Headless MCP status reporting and connecting reminders now match actual server handshake state. • MCP tool searches and calls now render with query, results, arguments and output on the daemon path. • Swift string interpolation with nested parentheses now highlights correctly in the TUI. • Copy-paste in --minimal mode no longer inserts extra blank lines or breaks long paths at wrap points. • /memory modal now shows copy confirmations, searches note contents, and works on narrow terminals. •

Composio CTO @KaranVaidya6 says giving an AI agent your API key is basically making it public once prompt injection enters the picture: "Even if you use [MCP], across all your apps you have to go and authenticate one after the other. If you use Codex, if you switch to ChatGPT, Claude Code, you'll have to do it all over again." "In some cases where MCPs don't exist, you have to literally share the API keys to the agent, which is definitely not secure. It's kind of giving your API key to public." "At some point the agent will find some link which will have prompt injection, and you'll be in a bad place where your key is gone and all your data is public." "We launched Shared Connections where you can share, let's say, an analytic software across the team, or DataDog for debugging, so you don't have to share one password or API keys to every single person." @composio

TradingView just shipped its new official MCP server for Claude. Your AI agents can control your charts, set price alerts, conduct research & more by pulling directly from your TV account. If you want to set up the updated connection, do this: Step One: Copy this link: Step Two: Open Claude, go to Settings → Connectors → Add custom connector, then paste the link there Step Three: Sign in to TradingView & approve access Step Four: Start prompting Example prompts: → "Pull the current support/resistance setup on [ticker] and give me the bull and bear case with key levels" → "Find stocks showing bullish RSI divergence on the 4H timeframe right now" → "Give me a full read on [ticker]: trend, momentum, support and resistance, and any active chart patterns" → "What are today's biggest news movers? Also, give me an update on any important upcoming events." → "Set an alert for when [ticker] closes above [level], and tell me the moment my watchlist hits any of my invalidation

• mcp.tradingview.com

很多知识库只解决“搜到文档”，WeKnora 想继续解决“理解、推理和持续整理”。 它把原始资料接入三条工作流：日常查询走 RAG；复杂问题交给 ReAct Agent 编排检索、MCP 工具与沙箱；Wiki 模式则把文档整理成可维护、互相链接的 Markdown 知识库，并提供知识图谱、版本历史和回滚。 项目支持 PDF、Word、图片、Excel、XMind 等格式，也能同步飞书、GitLab、Notion、语雀等来源；模型、向量库和存储后端可替换，并提供自托管、RBAC、审计与 Langfuse 可观测性。更适合需要私有部署和长期维护企业知识资产的团队。

• github.com

Use your agent to make healthcare videos with HeyGen. Connect the MCP to whatever you already work in and one prompt turns into a whole library. Every visit type, every procedure, every question a patient asks, same face and voice across all of it.

• developers.heygen.com

Introducing the Knowledge Base MCP. Greptile maintains a detailed knowledge base of how every part of your codebase works, as well as a history of past incidents. Starting today coding agents like Codex, Claude can access the Knowledge Base via Greptile's MCP, so they can use Greptile's learnings to write better code.

I just added a filter by @handle for Stalkr. It shows all the mentions from a specific account. And it works with analytics, so you know how a person talks about your brand online. + Available via API/MCP too

Mon vieux workflow : 1→ Je pensais et rédigeais tout dans Claude 2→ Je copiais dans un template 3→ Je passais 1h à corriger les polices et la mise en page Les étapes 2 et 3 viennent de disparaître.

@Templafy

Your AI can think. Can it finish the job? Templafy MCP turns work from @ChatGPT, @claudeai & @Copilot into branded, compliant, business-ready PowerPoints. > No copy-paste. No reformatting. No AI slop. > Best part? It's free for you to try 👉

• templafy.com

让 Agent 做一份幻灯片，吐出来一个 HTML 文件，标题位置不对想挪一下，只能回聊天框再打一行字，改完别处又跑偏。 Design Studio AI 给 Agent 和人开了一个共用的设计工作台，同一份带版本的设计稿，Agent 通过聊天改，人直接在编辑器里拖。 能做的内容有六类，网页界面、幻灯片、报告、线框图、3D 场景和时间线动画视频，从一句需求或者一个模板起手，先看预览再一处一处改。 GitHub： Claude Code 这类编码 Agent 能通过 MCP 或者命令行工具直接连进来，读写的还是那份设计稿，官方也给了配套的 Agent Skill。 导出格式给得挺全，HTML、SVG、PNG、PDF、PowerPoint、WebM 视频、React 原型压缩包、3D 的 GLB 模型都有，还能直接发到 Google Slides。 生图、配音、生视频这些接自己的模型账号，有在线版可以直接用，也能用 Docker 部署到自己服务器上，数据存本地。

• github.com

Create new ad variations in seconds with the ElevenLabs MCP. Take your top-performing Meta ads and swap the characters, outfits, products, locations, or languages. Instead of briefing a new shoot, remix the ad that already converts and extend its life across new audiences and markets. Try it now.

Google Home MCP lets Antigravity, Claude, OpenClaw, & more control your smart home by @technacity

• 9to5google.com

You can now train and run 500+ models locally with our Unsloth Docker image! 🐳 Use our new GUI or notebooks workflow. No setup required. Works on NVIDIA and AMD. Guide: GitHub:

@UnslothAI

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. > • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere > Unsloth Desktop is now available on and GitHub. > GitHub:

• unsloth.ai
• github.com
• unsloth.ai
• github.com

AI agents are starting to look less like chat bots and more like actual work environments. These 5 open-source projects show how far that idea is already going: 1. Agency Agents: A collection of specialized agents that can take on different roles and work together as an AI team. 2. Agent-Reach: Gives agents access to information across different websites and platforms, making web research much less limited. 3. Orca: Lets you run multiple coding agents on the same task, work on their changes separately, and compare the results. 4. OpenMontage: Turns an AI coding agent into a video production workflow, covering things like research, scripting, assets, editing, and rendering. 5. Codebase Memory MCP: Builds a map of your codebase so coding agents can understand how different parts of a project connect and keep that context across tasks.

• github.com
• github.com
• github.com
• github.com
• git

I'm excited to share that Zapier MCP is powering the new Claude for Small Business! Now, when Claude for Small Business needs an app it doesn't natively connect to, Zapier MCP is used automatically. It runs on the Claude connector we already have and has already been installed over 775k times. That means instant access to 9,000+ tools, plus we’ve added 40+ ready-made Cowork skills for running, growing, and enabling your business. Like /close-month to close out your books, or /monday-brief. Connecting all your apps to Claude is work nobody wants to do. We did it for you.

• zapier.com

声音克隆和视频配音，也可以完全留在本地。 VoiceStudio 是今天 GitHub Trending 上值得看的本地优先项目，页面截取时显示新增 2,072 stars。 它把 16 个 TTS 引擎、11 个 ASR 引擎放进同一桌面工作台，覆盖声音设计、语音转换、视频配音、听写、转录、多角色有声书与批处理；支持 macOS、Windows、Linux、Docker，还提供本地 API 与 MCP Server。 亮点不是“646 种语言”这个数字本身：项目明确说明实际覆盖与质量取决于所选引擎。它目前仍是 active beta，main 分支也可能变化。 适合重视隐私、离线流程和可控成本的创作者。

• github.com

You know that REST API that a bunch of your apps use? If you want, you can expose it as an MCP tool form LLMs without changing a thing. @GoogleCloudTech API Gateway now acts as a remote MCP server where you expose REST APIs as MCP tools. Docs:

• docs.cloud.google.com

Grok Build just got a pretty substantial upgrade across MCP, memory, long-running sessions, and overall agent reliability MCP tools can now return structured JSON, cancelled tool calls actually tell the server to stop working, memory can be managed directly from the /memory browser, and long-running sessions keep their compaction checkpoints instead of losing them during cleanup There are also fixes for macOS image pasting, subagent cancellation states, /rewind, huge skill files flooding context, Windows cloning, and minimal-mode session handling A lot of edge cases cleaned up here...especially for people running heavy agent workflows for long periods Release Notes: v1.0.33 Features: • MCP tool results now include structured JSON data when the server provides it. • GROK_GROVE=1 now enables both clone and worktree features when specific knobs are unset; missing remote settings no longer force copy. • Delete memories from the /memory modal using two-press x; only actual notes (not generated indexes) can be

Anthropic shipped Cowork inside the desktop app and a 14-step method turns a chat window into an autonomous coworker built on six blocks: a brain file, skills, connectors, plugins, a project workspace and scheduled tasks that run alone on a cadence. → Brain file: one markdown with role, voice and rules read before every task → Skills: a SKILL.md folder where good and bad examples make your taste the permanent rule → Connectors: MCP reach into Gmail, Calendar, Notion, Slack and Drive so outputs land in your inbox, not a draft → Scheduled tasks turn a helper into an operating system, morning brief, weekly report, monthly audit

We open sourced BrowserSkill, a bridge between your agent and your actual browser. most tools give the agent a blank browser. We let it borrow a tab from yours, then hand it back. > login state is already there, it just works where you're signed in > captchas and confirmation dialogs come back to you, then it continues > it's a CLI, not an MCP server => any agent that can run a shell can use it, and you see every call it makes one thing that's easy to miss: the agent asks before borrowing a tab, and that switch lives in your browser settings, not in a flag, so it can't be talked around. one line to install, works with Cursor, Claude Code, Codex, Hermes, Openclaw, CodeBuddy, WorkBuddy. Everything runs locally, MIT.

• github.com

Agent TARS brings GUI control and vision into your terminal, browser, and product — a full multimodal agent stack that completes tasks the way a human would navigate them. CLI and Web UI included. MCP ready out of the box. Github:

• github.com

DAILY AI BRIEF 🗞 — Sept 16 GOOGLE 🔥: - Gemini 3.8 Live and 3.8 Live Extended Thinking are out. 97-language auto-detect, near real-time vision, background tool calling. - Live is in Search Live plus Gemini API public preview. Extended Thinking is in Gemini Live, with Pro/Ultra getting it in Docs, Gmail, and Keep. - Gemini Notebook Voice Mode hits Ultra this week, Pro soon. Mobile voice recorder starts next week for all users, English first. - Interactive Reports for Gemini Notebook roll out to everyone in the coming weeks, plus new quiz formats and 60-second video overviews. OPENAI 🔥: - Sam declared a big ship week, then a much larger wave for DevDay. GPT-6 Sol and Luna are the expected drops. - GPT-5.5 leaves ChatGPT, Work, and Codex on Oct 14. Switch to GPT-5.6 Sol or GPT-6 Astra; the API keeps 5.5. XAI 🔥: - Grok Imagine can now edit text on any image in beta — color, size, font, alignment. - Grok Build 1.0.33: structured MCP JSON, in-UI memory deletes, and long-session checkpoints that survive cleanup.

5 OPEN-SOURCE AI AGENT REPOS EXPLODING ON GITHUB: Agency Agents — Agent-Reach — Orca — OpenMontage — Codebase Memory MCP — TOGETHER THEY COVER AI TEAMS, WEB RESEARCH, CODING AGENTS, VIDEO PRODUCTION AND CODEBASE MEMORY.

• github.com
• github.com
• github.com
• github.com
• github.com

Voice, music, image, and video generation now run inside the assistant you already work in, and everything you make lands in your ElevenCreative workspace. Open it in Studio to refine narration, layer in music and sound effects, and export.

@ElevenLabs

Introducing voice, music, image, and video generation in the ElevenLabs MCP. > Generate speech, transcripts, dubs, music, sound effects, images, and video from the assistant you already work in.

DeepSeek Harness 最新的 v0.1.6-alpha.1 同时新增实验性 Browser Use 和 Computer Use。模型现在既能直接操作网页，也能查看并控制本地桌面。 Browser Use 支持 Playwright MCP、Chrome DevTools MCP 和 Stagehand，可以直接操作网页。 Computer Use 则接入 Cua Driver，可找到具体 App 和窗口、获取当前界面截图，再根据界面元素或坐标执行点击和输入。官方提供 MCP 和原生两种 Computer Use 接入方式，原生方式可以直接集成进 Harness，不需要另外安装独立的 Cua Driver App。 两项能力目前都属于实验性功能，需要手动启用。Computer Use 还需要给实际运行它的应用授予屏幕读取和电脑操作权限。

Wow... this is very cool.

@tonysimons_

I just found a repo that lets AI agents control a VIRTUAL IPHONE. > Not the iOS Simulator. > Actual virtualized iOS on Apple Silicon. > Screenshots. Touch. Swipes. Typing. Apps. > There’s even an MCP server for coding agents. > +633 stars TODAY. >

• github.com

Just shipped our video editor MCP for @floraai today - Amazed what Astra can do with it

Drop one picture into an AI agent and come back to a full 3D street. Shops, signs, road, sky, all built without anyone opening a 3D tool. GPT-6 Astra and Hyper3D MCP just did in one run what used to take a whole team.

@DeemosTech

One image. One Agent. One scene. > @OpenAIDevs GPT-6 Astra (Codex) + HYPER3D MCP just showed us the second half of 3D gen. 🚀

太魔幻了，Astra 还在让大家惊叹：AI 终于会用 Blender 了。 结果Nex-AGI 已经直接出现在现实世界里了。 我只给了一个 Prompt： 做一根 6cm 的粉色活动香蕉，省点料。 然后我基本没碰 Blender。 它自己用 MCP 建模，Computer Use 看结果、自己修，最后直接吐给我一个 STL。 我顺手扔进拓竹。 👇 视频里正在一层一层长出来的，就是它自己设计的香蕉。 这一刻我是真有点惊到了。 Nex-AGI + Computer Use，能力完全超出我预期。 一句话 → Blender → STL → 3D 打印 → 实物。 🔥 这真的有点科幻了。 直接免费体验nex-agi ：

• openrouter.ai

opennews-mcp 是一个把各大金融消息源汇到一起的 MCP，装进 Claude Code 后用聊天就能问最近有什么值得注意的动向。 一共接了 85 个以上的数据源，分成新闻、交易所上币、链上大额、市场异动、预测信号几类，光新闻类就占了 55 家。 GitHub： 每条消息都过了一遍 AI，打一个 0 到 100 的影响力分，标出偏多还是偏空，再配一段中英文摘要。 链上那块还能盯着大额的交易和持仓变动，市场那块可以查看啊资金费率、大额爆仓这些异常。 用之前需要先配置 API Key。除了盯盘之外，还想让消息面也自动汇总的朋友，可以接进去试试。

• github.com

Goodbye, Postman Developers use your APIs. Now agents do too. Today, we’re launching @elvabytheneo , our biggest launch ever. Connect your codebase and Elva: → Discovers your APIs, no spec required → Builds and categorizes your API catalog → Maps usage across services → Checks security and AI readiness → Creates controlled API contracts for humans and agents → Publishes hosted MCP servers with auth and analytics → Tracks changes as your code evolves Some of our customers already receive more API calls from agents than humans. API management needs to catch up. Elva is now open to everyone. Try it with your own repo and tell us what we’re missing.

Grok Build just got another update focused on making multi-agent sessions easier to read and navigate Subagent groups now clearly show how many agents are still running versus finished, dashboard search and resume selection behave more predictably, cancellation banners show the actual cause, and long paths are cleaned up across headers and dashboards MCP handling also gets a useful fix....tools with long server prefixes are no longer silently dropped Another small release that makes busy agent sessions much easier to understand at a glance Release Notes: v1.0.31 Bug Fixes: • Folded subagent groups in scrollback now correctly label how many are still running versus completed. • Dashboard search and the resume picker now clearly indicate the active text field and restore list selection after search. • Dock sections no longer keep a selection highlight after you collapse them with a click. • Worktree paths no longer show an extra suffix in the header or dashboard. • MCP tools with long server prefixes are n

平时在 Mac 上干活，偶尔要回家里那台 Windows 上取个文件、跑个只有 Windows 才有的软件，商业远程软件不是限速就是要买会员。 YourDesk 是一款 macOS 和 Windows 互连的远程桌面工具，输入对方 ID 和密码就连上，源码在 GitHub 公开，个人和公司内部用都免费。 编解码走硬件加速，Mac 上 H.264 和 HEVC，Windows 上 H.264 和 AV1，两端按各自能力自动选，工具栏能看到当前用的是哪种。 跨电脑复制粘贴是我觉得最实用的一点，文字、图片、文件、整个文件夹都能复制过去直接粘贴，一批最大 2GB。 GitHub： 多显示器在工具栏中间直接切，最多 4 个屏。远端分辨率高的话可以开画面增强，先压低传输再本地放大，4K 桌面效果更明显。 新版加了 MCP，AI Agent 能自己连上远程电脑，操作桌面或命令行，干完活断开。这个功能默认关着，开了也只放行本机来源。 除了桌面模式还有远程命令行模式，Linux 机器也能当命令行被控端。Mac 端是签过名过了苹果公证的 DMG，Apple Silicon 专用。

• github.com

Controls FreeCAD from Claude Desktop to design models, run Python scripts, and perform finite element analysis.

• github.com

CloddsBot 这个开源项目最近在 GitHub 上很火，作者是在一场 Agent 黑客松花费 12 天时间做出来的。 一个跑在自己电脑上的 AI 交易终端，底层用的是 Claude，用聊天的方式就能看盘和下单。 覆盖 10 家预测市场、7 家合约交易所，外加 Solana 和 5 条 EVM 链上的去中心化交易所。 支持接入 Telegram、Discord、WhatsApp、Slack 等社交渠道。 GitHub： 内置 118 种策略，鲸鱼地址追踪、跟单、定投机器人都有，风控带熔断、每日亏损上限和一键停机。 还有 121 个 Skill，也能当 MCP 工具挂在 Claude Desktop 和 Claude Code 使用。

• github.com

this guy built a robinhood chain tool that makes his ai check the pool before it talks about his bag meet TRENCH give an MCP-compatible agent a token address and a USD position size: → reads public Robinhood Chain pools through DexScreener → checks the chain and latest block through RPC → selects the highest-liquidity observed pool → models how the position size presses against estimated depth → returns a DEEP / THIN / CRITICAL grade, the reason and the assumptions → lets the agent explain the evidence a token can have the same price, the same chart and the same pool - and still be a very different problem at $500 versus $5,000 that's the part he wanted the agent to calculate instead of hand-wave the loop is: TOKEN + SIZE → PUBLIC DATA → PRESSURE MODEL → AGENT EXPLANATION five read-only MCP tools, open source, a browser playground anyone can try without installing anything the browser uses manual inputs, the MCP server is where live token data comes in, neither is an executable sell quote no private