内容
精选全部 AI 动态热点榜AI 日报主题收藏
模型
模型榜Tibo重置监控
更多
Agent 接入关于更新日志反馈
京ICP备2026012723号-5
精选全部日报更多
反馈

全部 AI 动态

全部动态X · 549 条
来源全部一手资讯X
类型全部
全部模型产品行业论文教程观点
标签「MCP/工具调用」清除
全部 AI 动态
全部模型产品行业论文教程观点
推文 · 标签「MCP/工具调用」 · 549 条清除

9月23日今天9月23日 周三

星期三 · 3 条
🚨 AI News | TestingCatalog@testingcatalog02:59
AI 评分 54/100
DigitalOcean 推出 Managed Agents 公测，支持 Claude Code、Codex 等智能体运行时DigitalOcean launched Managed Agents on its platform, supporting agent harnesses including OpenCode, Codex, and more. Managed Agents on DigitalOcean can connect to 16,000+ tools and are integrated with its native Inference Engine.Harness Runtime runs every session in an isolated microVM within a coding sandbox.Sessions persist after a device disconnects and resume from pause in 305 milliseconds.Action Gateway offers governed access to over 16,000 tools through the same MCP endpoint.译DigitalOcean 推出 Managed Agents，现已进入公开预览，可运行 Claude Code、Codex 或自建 LangGraph 智能体，并提供 75 个以上开放与专有模型可选。

DigitalOcean: DigitalOcean Managed Agents is now in public preview. Run Claude Code, Codex, or your own LangGraph agent in a runtime e...

智能体MCP/工具产品更新
🚨 AI News | TestingCatalog@testingcatalog01:59
AI 评分 54/100
DigitalOcean 推出 Managed Agents，支持 OpenCode、Codex 等智能体框架DigitalOcean launched Managed Agents on its platform, supporting agent harnesses including OpenCode, Codex, and more.Managed Agents on DigitalOcean can connect to 16,000+ tools and are integrated with its native Inference Engine.Harness Runtime runs every session in an isolated microVM within a coding sandbox.Sessions persist after a device disconnects and resume from pause in 305 milliseconds.Action Gateway offers governed access to over 16,000 tools through the same MCP endpoint. https://x.com/digitalocean/status/2102414817797550320/video/1译DigitalOcean 在其平台推出 Managed Agents，支持 OpenCode、Codex 等智能体框架，并与原生 Inference Engine 集成。Harness Runtime 在编码沙箱内的隔离 microVM 中运行每个会话，设备断开后会话仍持续、从暂停恢复仅需 305 毫秒；Action Gateway 通过同一 MCP 端点对 16，000+ 工具提供受管访问。
智能体MCP/工具产品更新部署/工程
elvis@omarsar000:12
AI 评分 56/100
DigitalOcean Managed Agents 开启公开预览DigitalOcean Managed Agents are here!They work with major harnesses like Claude Code and Codex.16,000+ tools. Idle agents stop using CPU.Optimized to help builders scale agents in production. Worth checking out.译DigitalOcean 宣布 Managed Agents 进入公开预览，可运行 Claude Code、Codex 或自己的 LangGraph 智能体，空闲时暂停、仅按活跃时间计费。

DigitalOcean: DigitalOcean Managed Agents is now in public preview. Run Claude Code, Codex, or your own LangGraph agent in a runtime e...

智能体MCP/工具产品更新
另有 1 家信源报道X：Rohan Paul (@rohanpaul_ai)

9月22日9月22日周二

星期二 · 1 条
ViggleAI@ViggleAI03:06
AI 评分 51/100
Viggle 发布 PINOC MCP：面向 AI 智能体的角色动画引擎Introducing PINOC MCP: the character animation engine for AI agents.Your agent builds the game, then calls PINOC to:• generate rigged, animated Gaussian splat characters • drive your own mesh with text-to-motion, video-to-mocap, or our preset motions.Comment & RT to win 300 free credits!译Viggle 发布 PINOC MCP，定位为 AI 智能体的角色动画引擎，智能体在搭建游戏或 3D 场景后调用 PINOC 生成已绑定骨骼的动画 Gaussian splat 角色。它还支持用文生动作、视频转 mocap 或预设动作库驱动自有 mesh；引用推文称整条宣传视频（含屋顶跑酷游戏）由 GPT-6 Astra 加 PINOC MCP 制作。

PINOC: GPT-6 Astra can build games or 3D scenes fast. But getting characters to move is still hard. You browse the Mixamo prese...

智能体MCP/工具产品更新视频

9月21日9月21日周一

星期一 · 1 条
凡人小北@frxiaobei22:29
AI 评分 66/100
Cloudflare Python Workers 正式 GA，Python 成为平台一等支持语言用 Python 做 AI 应用的朋友，有福了。 可以看看 Cloudflare 这次的更新。Python Workers 正式进入全面可用阶段（GA）。写好的 Python 应用，可以直接部署到 Cloudflare，由平台负责运行和扩容。看点有四：1. 熟悉的框架可以继续用。FastAPI、Django、Flask 都支持，不用为了部署到 Workers 换一门语言，也不用自己配置传统的 Web 服务器。2. 数据库、存储、队列接起来也更顺了。Python 可以直接调用 Cloudflare 的 R2、D1、队列和工作流，不用再手动把 Python 对象转换成 JavaScript 对象。底层网络能力也补上了，可以通过 Hyperdrive 连接 PostgreSQL、MySQL。3. 做 Agent、MCP、RAG 更方便。OpenAI SDK、LangChain、MCP 等 Python 库可以在 Workers 里运行。接收请求、排队、调用模型、保存结果，一整套流程都能用 Python 串起来。官方 blog 也给了 MCP 服务、RAG 和图片生成工作流的示例。4. 但是，别急着把现有项目整个搬过去。支持 Python 框架，不代表所有依赖都能跑。底层是 WebAssembly，带 C、C++、Rust 扩展的包需要适配；长任务和有状态的 Agent，也得结合平台限制来设计。接入的 Cloudflare 服务越多，以后迁移要做的改动也越多。对个人开发者和小团队来说，这种更新挺实在。功能写出来以后，部署、扩容、接数据库这些事，往往还得花不少时间。如果本来就在用 Cloudflare，可以先拿一个小 API 或 MCP 服务试试，把依赖兼容性和实际费用跑明白，再决定要不要搬更大的项目。译Cloudflare 宣布 Python Workers 正式进入全面可用阶段（GA），Python 成为 Cloudflare 开发者平台的一等支持语言，应用可直接部署并由平台负责运行和扩容。

Cloudflare: We're excited to announce that today Python Workers are generally available (GA). It means Python is now a first-class, ...

智能体MCP/工具产品更新部署/工程
另有 1 家信源报道Hacker News 热门（buzzing.cc 中文翻译）

9月18日9月18日周五

星期五 · 1 条
Tripo@tripoai17:21
AI 评分 59/100
ComfyUI 动画工作流：概念图经 Tripo 生成 3D 模型再转任意角度Thrilled to see Tripo powering the 3D generation step in this incredibly smooth @ComfyUI animation workflow. From concept art to any angle in seconds.Check out the magic below ↓译ComfyUI 分享一个概念图转任意角度的动画工作流，其中 3D 生成步骤由 Tripo 完成。工作流分三步：概念图经 Tripo 生成并保存为 GLB 模型；静止画面用 Load 3D 输出视角后由 GPT Image 2 渲染成同风格插画；镜头运动则在视口中录制路径，作为 Seedance 2.0 的运动参考生成镜头。文末附工作流运行链接。

ComfyUI: ComfyUI for Animation: Concept Art to Any Angle Concept art → 3D proxy → any angle you want. One graph, two methods. Ste...

MCP/工具图像生成教程/实践

9月16日9月16日周三

星期三 · 2 条
DAIR.AI@dair_ai12:29
AI 评分 56/100
研究显示仅提供不必要工具即可让 LLM 作答率从 98.2% 降至 63.5%Giving an assistant extra tools seems harmless.Surprisingly, this paper shows it can make the assistant stop answering questions it knows.Across six models, the answer rate on questions that need no tool fell from 98.2% to 63.5% when a related tool was merely available.So the drop comes from the tool being present, even when it goes unused.The benchmark has 500 query pairs across 10 domains, each with a tool-unavailable control. A preceding tool call recovered some lost answers and caused new losses.A one-sentence system instruction that tells the model what the tool is for recovered up to 45.6 points.Paper: https://academy.dair.ai/papers/when-tools-get-in-the-way-the-effect-of-unnecessary-tool-availability-on-llm-ans-2609.14157译一篇论文发现，仅仅让相关工具可用就会使大语言模型放弃回答本可直接答的问题，六个模型的作答率从 98.2% 降至 63.5%，即使工具从未被调用。基准含 10 个领域 500 组查询对并设无工具对照；前序工具调用会挽回部分丢失答案但引入新损失，一句说明工具用途的系统提示词最多挽回 45.6 个百分点。
智能体MCP/工具论文/研究
Rohan Paul@rohanpaul_ai07:42
AI 评分 57/100
Plasma__AI 推出 Radio，让 Claude、Codex、Grok 等智能体在同一房间直接对话The human is still doing a surprising amount of routing in multi-agent workflows.Copy Claude's output into Codex. Bring Codex's result back to Claude. Explain to another agent what changed. Repeat.@Plasma__AI launched Radio, and it gives Claude, Codex, Grok and other agents 1 shared room to talk directly.a shared chat room where humans and agents from different providers can talk in the same thread, so Claude Code, Codex, Cursor, OpenCode, Grok and other agents no longer need a person copying outputs from 1 tool into another.Most multi-agent systems keep coordination inside an orchestrator, meaning a controller routes tasks and passes messages behind the scenes, while Radio exposes that communication layer directly:a user creates a channel, copies its link, gives it to 1 or more agents, and those agents can join the room, read the same conversation, reply to the human, and reply to each other.Any agent that can fetch a URL can join, the room can span different machines and teammates, and the human can steer the work from another device, which makes the same channel useful for PR reviews, debugging, splitting a task across agents, or letting a local coding agent work with a cloud agent.The channel also becomes the record of the work, so instead of reconstructing why 1 model made a decision from separate chat windows, the whole exchange stays visible in 1 place.and no sign-up is required to create a channel here.译@Plasma__AI 推出 Radio，为 Claude、Codex、Grok 等不同厂商的智能体提供共享聊天房间，免去人工在工具之间复制输出。用户创建频道并分享链接，能获取 URL 的智能体即可加入，读取同一对话并回复人类和其他智能体，频道记录全程可查，且创建频道无需注册。
智能体MCP/工具产品更新

9月15日9月15日周二

星期二 · 5 条
Rohan Paul@rohanpaul_ai08:12
AI 评分 56/100
Plasma AI 推出 Radio：让不同提供商的智能体在共享聊天室中协作Multi-agent systems usually hide the coordination layer inside an orchestrator.@Plasma__AI Plasma AI launched Radio, and puts that coordination in a room you can actually watch.Radio is a shared chat room where agents from different providers can talk directly. Without a shared channel, each agent sees only its own conversation, leaving humans to relay outputs between separate tools.Radio replaces that handoff with a link, and Plasma says any agent that can fetch a URL can join, including Claude Code, Codex, Cursor, OpenCode, and Grok.译Plasma AI 推出 Radio，一个面向智能体的共享聊天室，创建频道、分享链接即可让队友和智能体加入，无需注册。Radio 将多智能体系统中通常隐藏在 orchestrator 里的协调层变成可见的房间，任何能抓取 URL 的智能体都可加入，包括 Claude Code、Codex、Cursor、OpenCode 和 Grok。网址 https://radio.plasma.ai

Plasma AI: Introducing Radio: A chat room for your agents. Create a channel, share the link, and bring your teammates and agents to...

智能体MCP/工具产品更新
另有 1 家信源报道X：Elvis Saravia (@omarsar0, DAIR.AI)
Rohan Paul@rohanpaul_ai07:12
AI 评分 55/100
Rohan Paul 用 ElevenLabs MCP 同一提示词对比四个模型表现There is a big difference between model access and model optionality.I tried the same prompt on four models this morning. Only one handled the hard-light constraint the way I wanted.With the models sitting behind the same MCP, I don't really have to "pick a model" anymore. I can run the task, see where each one breaks, and use the one that actually gets it right.译Rohan Paul 转引 ElevenLabs 在 MCP 中新增语音、音乐、图像和视频生成功能，可生成语音、转录、配音、音乐、音效、图像和视频。作者用同一提示词在四个模型上测试，只有一个符合硬光约束，并认为模型放在同一 MCP 后无需预先选型，跑任务看各自表现即可选用合适的那个。

ElevenLabs: Introducing voice, music, image, and video generation in the ElevenLabs MCP. Generate speech, transcripts, dubs, music, ...

MCP/工具多模态现象/趋势
🚨 AI News | TestingCatalog@testingcatalog06:59
AI 评分 55/100
ElevenLabs 在 MCP 中加入 ElevenCreative 工具套件，支持生成语音、音乐、音效、图像和视频ElevenLabs has added its ElevenCreative suite of tools to the ElevenLabs MCP.It lets users generate speech, music, sound effects, images, and video inside the assistant where they write.The new connector lets users write the script in the assistant, then create the voice, soundtrack, and visuals in the ElevenLabs app and bring them back. Users can now get the finished audio or video as the output of the same request, so you can hear the script while it is still being written.Over 50 models are available through the connector in Claude, ChatGPT, and Cursor. https://x.com/ElevenLabs/status/2099547227223908568/video/1译ElevenLabs 将 ElevenCreative 工具套件加入 ElevenLabs MCP。用户可在助手内写脚本、配音、配乐并生成视觉内容，同一请求即可输出完成的音频或视频；连接器在 Claude、ChatGPT 和 Cursor 中提供超过 50 个模型。
MCP/工具产品更新多模态语音
🚨 AI News | TestingCatalog@testingcatalog02:29
AI 评分 52/100
Perplexity Portable Computer 扩展到 Windows RTX GPU 设备并支持本地 MCPPERPLEXITY 🔥: Windows users with NVIDIA RTX GPUs can now use Portable Computer powered by local models!Support for local MCPs and scheduled tasks has also been added. Earlier, Portable Computer was introduced for NVIDIA DGX Spark devices. Now, Portable Computer is also available on Windows PCs with a supported NVIDIA RTX GPU with 24GB of VRAM or higher.Models available locally 👀 • PPLX 27B (Perplexity post-trained Qwen 3.8 27B) • Qwen 3.8 27B (stock) is not available on Windows • Nemotron 3.5 Lightning (~30B MoE, ~3B active) is marked as "Coming Soon" https://x.com/perplexity_ai/status/2099514386193027201/video/1译Perplexity 将 Portable Computer 从 NVIDIA DGX Spark 扩展到配备 24GB 及以上显存 NVIDIA RTX GPU 的 Windows 电脑，由本地模型驱动，并新增本地 MCP 和定时任务支持。
MCP/工具产品更新端侧
另有 3 家信源报道IT之家（RSS）X：Perplexity (@perplexity_ai)NVIDIA Blog（RSS）
elvis@omarsar001:12
AI 评分 59/100
Elvis Saravia 分享从零构建 agent harness 的入门指南On building an agent harness from scratch.Got so many questions about where to get started.My short guide (feed it to your agent):If you really want to learn harnesses well, it's worth building one from scratch using a programming language (TypeScript or Python) of your choice.When I got started, I implemented my first harness using ReAct from Google: https://academy.dair.ai/papers/react-synergizing-reasoning-and-acting-in-language-models-2210.03629At the time, I built this from scratch, but you can easily prompt your agent to consume the paper and produce a minimal implementation you can inspect and understand.You want to target having three parts:• an LLM module for all things inference, and it should ideally support several models. I used OpenRouter when I got started. This can include the system prompt, but you can also separate it out if you plan to explore context-engineering ideas more deeply.• a tools module (I recommend building them as MCP tools for interoperability, but you can design functions from scratch if you have experience).• an agent loop that encapsulates the tools and LLM. ReAct is one of the more basic loops you can implement.Primarily, aim to understand the main components and how they work with each other.Pro tips:• try to keep your system prompt minimal and experiment with different models; a mini version of all frontier lab models should be good enough to get you started.• look at the code and log things as you experiment with different tasks. You want to log inputs/outputs to the loop, inputs/outputs from LLMs, and inputs/outputs from tool calls as a starting point. Set up a simple set of diverse tasks to test your agent loop on. So with every change, you can run the tasks and inspect the results manually.Once you have a good grasp of this, you can easily add other things like skills, memory, etc., once you have a good idea of how to tune them. It helps to keep things modular if you are planning for this. I would recommend playing with memory, skill, and subagent as good next steps.If you don't want to build the components or want to start building a more serious agent harness, I recommend using the Pi SDK or LangChain harness tools. I am also going to release something soon to help with this.Let me know if you have questions. I am planning a longer write-up on this, but this should be enough to give you something to experiment with.译DAIR.AI 的 Elvis Saravia 分享从零构建 agent harness 的入门指南，建议用 TypeScript 或 Python 实现包含 LLM 模块、tools 模块和 agent loop 三部分的最小 harness，并以 ReAct 作为入门循环。
智能体MCP/工具教程/实践

9月14日9月14日周一

星期一 · 1 条
SenseTime@SenseTime_AI23:06
AI 评分 58/100
商汤开源 SenseNova Skills 办公技能套件，可将原始数据处理成可编辑 .pptxThanks to Flash Cash for reviewing our 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗼𝗳𝗳𝗶𝗰𝗲 𝘀𝗸𝗶𝗹𝗹 𝘀𝘂𝗶𝘁𝗲!Instead of switching between separate tools, 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗦𝗸𝗶𝗹𝗹𝘀 integrates 𝗗𝗲𝗲𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵, 𝗗𝗮𝘁𝗮 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀, 𝗣𝗣𝗧 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻, and 𝗜𝗻𝗳𝗼𝗴𝗿𝗮𝗽𝗵𝗶𝗰 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻—processing raw data into editable .pptx decks.Built for any skills-compatible agent, including OpenClaw and hermes-agent.👉 ＧitHub https://github.com/OpenSenseNova/SenseNova-Skills ⚡ Quick installation (bundled with Hermes Agent & OpenClaw) https://github.com/OpenSenseNova/SenseNova-Skills/blob/main/INSTALL.md 👾 Discord https://discord.gg/BuTXPHmQub🎥 Watch the breakdown: https://m.youtube.com/watch?v=RLvqfyalo-8译商汤宣布开源 SenseNova Skills 办公技能套件，集成 Deep Research、Data Analytics、PPT Generation 和 Infographic Generation，把原始数据处理成可编辑的 .pptx 演示文稿。
智能体MCP/工具产品更新开源生态

9月11日9月11日周五

星期五 · 2 条
OpenRouter@OpenRouter21:07
AI 评分 55/100
Ling 3.0 Flash VL 上线 OpenRouter，由 Novita Labs 提供服务Ling 3.0 Flash VL is live on OpenRouter, served by @novita_labs.A 124B MoE with 5.5B active params, now with native image and video input plus visual agent capabilities. Hybrid instant and reasoning modes, with tool calling.https://openrouter.ai/inclusionai/ling-3.0-flash-vl:free译Ling 3.0 Flash VL 上线 OpenRouter，由 Novita Labs 提供服务，是一个 124B MoE、激活参数 5.5B 的模型。新增原生图像和视频输入及视觉智能体能力，支持即时与推理混合模式以及工具调用，提供免费入口 https://openrouter.ai/inclusionai/ling-3.0-flash-vl:free。
MCP/工具产品更新多模态推理
另有 1 家信源报道X：蚂蚁百灵 (@AntLingAGI)
Sherwin Wu@sherwinwu10:46
AI 评分 63/100
OpenAI 发布 Agents API，用 Codex 同款 harness 在云端构建 AgentFor those of you who want to build scaled agents for your firm, and then deploy them into your own internal AI application – this is for you!Quickly build agents that use the same harness as Codex / ChatGPT work, and then expose them however you want.译OpenAI 发布 Agents API，一种在云端构建 Agent 的新方式，底层由 Codex 所用的 harness 支持。用户可自带常用工具和连接器、连接任意沙箱，构建与 Codex/ChatGPT 相同 harness 的 Agent，并按需暴露到自己的内部 AI 应用中。

Steve ☕️: Today we're launching the Agents API, a brand new way to build Agents in the cloud, backed by the Codex harness. Bring a...

智能体MCP/工具OpenAI产品更新

9月10日9月10日周四

星期四 · 2 条
OpenRouter@OpenRouter23:07精选
AI 评分 65/100
OpenRouter 推出有状态 Shell 工具 openrouter：shell 并上线 Files APINew stateful server tool: Shell!Any model on OpenRouter can now run commands in a hosted Linux container and use the new Files API to move files in and out. Available today in beta: openrouter:shell译OpenRouter 推出新的有状态服务端工具 Shell，任何 OpenRouter 上的模型都可以在托管的 Linux 容器中运行命令。该功能今日起以 beta 形式提供，代号为 openrouter：shell，同时新增 Files API 用于在容器内外传输文件。
MCP/工具产品更新部署/工程
推荐理由：OpenRouter 官方介绍新 Shell 工具和 Files API 的能力与开放方式，模型调用方可以据此判断如何接入有状态命令执行。
Tripo@tripoai16:57精选
AI 评分 65/100
Tripo 展示 GPT-6 Astra 与 Blender MCP 结合的 3D Vibe Coding 实操工作流This is what 3D Vibe Coding looks like in practice.An incredible use case combining Tripo for high-quality 3D generation and Astra + Blender for editing and rigging.No complex 3D skills required — just prompt, generate, and refine. Read the full workflow below!译Tripo 转发用户案例，展示用 Images 2.5、Tripo 智能网格 P2.0、GPT-6 Astra 和 Blender MCP 以 AI 为主制作 3D 角色的完整流程。作者几乎只做视图操作，通过截图加参考图让 Astra 修正形状与纹理，并指出纹理修正在细节上仍较粗糙。作者称此前在 GPT-5.6 Sol 上反复失败的操作在 Astra 上可以直接完成。

🍣お寿司職人|AIゲーム・アニメ: 话题中的「GPT-6 Astra × Blender」，我实际体验了一下。 这个，相当震撼。 连 Blender 新手也能做到。几乎只靠视角移动（视图）的操作就能做到这个程度。 模型是 Tripo 制作的，舞台是在 Blender 上搭建的...

智能体MCP/工具图像生成教程/实践
推荐理由：原文给出完整的 12 步 3D 角色制作工作流和截图生成参考图的修正方法，Blender 初学者可以照着复用。

9月9日9月9日周三

星期三 · 1 条
elvis@omarsar021:40
AI 评分 51/100
Qodo 发布 Agentic Toolbox，为 Claude Code、Codex、Kiro 和 Cursor 提供独立审查能力Qodo just launched the Agentic Toolbox.It gives Claude Code, Codex, Kiro, and Cursor direct access to @QodoAI's review engine, codebase knowledge, and team rules.译Qodo 发布 Agentic Toolbox，让 Claude Code、Codex、Kiro 和 Cursor 直接访问 Qodo 的审查引擎、代码库知识和团队规则。该工具箱含 4 个技能并通过 MCP 提供，包括 codebase-wisdom、review、get-rules 和 review-resolver，背后依托关系图、PR 历史、工作区规则和 Live Git 状态等上下文；只有两个智能体无法达成一致的结论才交给人工，人工审查和 PR 关卡仍然保留。
智能体MCP/工具产品更新编码

9月8日9月8日周二

星期二 · 1 条
OpenBMB@OpenBMB01:07
AI 评分 54/100
面壁智能发布 MiniCPM5-2B，vLLM 稳定版提供 day-0 支持Thank you @vllm_project for the day-0 support 🙌译面壁智能（OpenBMB）发布 MiniCPM5-2B，vLLM 稳定版提供 day-0 支持。该模型为 2.6B Dense 模型，原生 131K 上下文，同一 checkpoint 支持 Think/No-Think 两种模式，并通过 vLLM 的 minicpm5 parser 支持工具调用。模型采用标准 LlamaForCausalLM 架构，权重与训练数据一同开放，部署配方见 http://recipes.vllm.ai/openbmb/MiniCPM5-2B。

vLLM: 🤝 Day-0 support for MiniCPM5-2B on stable vLLM. ⚡ Dense 2.6B model with 131K native context 🧠 Think / No-Think from th...

MCP/工具开源生态推理模型发布

9月6日9月6日周日

星期日 · 1 条
🚨 AI News | TestingCatalog@testingcatalog06:29
AI 评分 52/100
Gemini Business 支持自定义 MCP 服务器连接GOOGLE 🔥: Gemini Business now supports custom MCPs!New: custom MCP server connections - Connect private data and internal tools.It's happening! 🤯How long until we see them on consumer Gemini too?译Gemini Business 新增自定义 MCP 服务器连接功能，可连接私有数据和内部工具。截图显示 Gemini Enterprise 界面中出现该新功能提示，并提供 Add MCP server 入口。作者猜测消费版 Gemini 何时也会跟进。
GoogleMCP/工具产品更新

9月5日9月5日周六

星期六 · 3 条
Replit ⠕@Replit10:07
AI 评分 39/100
Replit 一周更新：MCP 转正、Project Analytics 与数据库备份This Week in Replit1) Replit MCP comes out of beta 2) Project Analytics: traffic, funnels, and experiments in chat 3) Database Backups: nightly snapshots for your production DBThread 🧵译Replit 发布本周更新汇总：Replit MCP 结束测试正式发布；Project Analytics 在对话中提供流量、漏斗和实验数据；新增 Database Backups，为生产数据库提供每夜快照。
智能体MCP/工具产品更新
Elon Musk@elonmusk05:41
AI 评分 51/100
Grok 上线 @Bot 模板市场，Haggle Bot 一周为团队节省超 $100KGrok @Bot templates.Try Haggle Bot for saving money on procurement! This is a gamechanger.译Grok 现在支持从 marketplace 添加 Bot templates。被引用的 @bot 介绍其团队的采购智能体 Haggle Bot，可谈判供应商合同、查找闲置 SaaS 席位并比价周期性采购，一周内节省超过 $100K。Elon Musk 推荐用 Haggle Bot 节省采购成本。

Grok Bot: You can now add Bot templates from our marketplace. We’re sharing Haggle Bot, our in-house procurement specialist. It ne...

智能体MCP/工具产品更新
Replit ⠕@Replit00:07
AI 评分 31/100
Replit 推出 Replit MCP，可在任意位置操控你的 AgentReplit MCP: Steer Your Agent From Anywhere https://x.com/i/broadcasts/1qGvveBrNMgGB译Replit 官方宣布推出 Replit MCP，用户可以在任何地方操控（steer）自己的 Replit Agent。官方还附带了一场直播广播链接（https://x.com/i/broadcasts/1qGvveBrNMgGB）用于介绍该能力。
智能体MCP/工具产品更新

9月4日9月4日周五

星期五 · 4 条
elvis@omarsar023:10
AI 评分 35/100
DAIR.AI 创始人分享用 Slack 智能体 Viktor 追踪 AI 论文的三周体验I read AI papers for a living, but it has become impossible to track insights.Every week I triage agent papers for our Top AI Papers of the Week digest.A few weeks ago, I tried @viktor_com, an AI employee that works inside Slack, in the channel where that triage happens.I asked it to go through the week's agent papers and pull three worth reading.It sent the list back that same morning.On day 19, it posted in the channel without being asked. "Six more landed overnight. One of them contradicts the routing section in module 4."Two days later, again without me, it drafted the correction and left it unpublished. 2,100 people are on that module.Everything it did came back as a proposal for me to approve. That is why I kept it running.Finding new papers is easy. Knowing when one of them breaks something is much harder - in my case, the course lessons I teach.If you run agents for weeks at a time, look closely at how the approval trail works. Happy to go deeper on this one.译DAIR.AI 创始人 Elvis Saravia 分享用运行在 Slack 中的 AI 智能体 @viktor_com 辅助筛选每周智能体论文的体验。第一天它按请求从当周论文中挑出三篇值得读的，当天早上返回；第 19 天它在未被要求的情况下主动发消息指出新论文与课程第 4 模块的路由部分相矛盾，两天后又起草了修改并保持未发布，该模块有 2100 名学员。
智能体MCP/工具大佬观点
Peter Steinberger 🦞@steipete11:04
AI 评分 21/100
Having a claw in your group chat is so useful！Having a claw in your group chat is so useful!
智能体MCP/工具教程/实践
ClaudeDevs@ClaudeDevs07:37
AI 评分 47/100
Anthropic 为 ant CLI 新增 ant apply，支持声明式管理 Claude Managed Agent 资源We've added ant apply to the ant CLI.Now you can declare Claude Managed Agent environments, agents, skills, memory stores, and deployments as files in your repository and keep the API's resources in sync with them using ant apply.Docs: https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply译Anthropic 的 Claude Devs 团队宣布在 ant CLI 中新增 ant apply 命令。用户可以在仓库中以文件形式声明 Claude Managed Agent 的环境、智能体、技能、记忆存储和部署，并通过 ant apply 让 API 资源与这些文件保持同步。文档见 https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply。
智能体MCP/工具产品更新部署/工程
OpenAI Developers@OpenAIDevs01:15
AI 评分 22/100
WebMCP Challenge 截止时间延长 12 小时至凌晨 1：00 PTFor everyone who said “just one more commit.”Deadline extended:译OpenAI 官方宣布 WebMCP Challenge 截止时间延长 12 小时，至凌晨 1：00 PT。官方称系统已完全恢复在线，延期为受当日故障影响的参赛者留出更多提交时间。

pranav: We're extending the WebMCP Challenge deadline by 12 hours to 1:00 am PT. While we're now fully back online, we wanted to...

MCP/工具OpenAI行业动态

9月3日9月3日周四

星期四 · 8 条
OpenClaw🦞@openclaw23:58
AI 评分 59/100
AWS Bedrock AgentCore Payments 正式 GA，OpenClaw 智能体可通过插件完成受控支付AgentCore Payments is now GA.OpenClaw agents can use the @awscloud aws-agents-pay plugin to make bounded, human-approved payments for paywalled APIs, MCP servers, and web content.OpenClaw walkthrough: https://aws.amazon.com/blogs/machine-learning/build-openclaw-agents-that-transact-with-amazon-bedrock-agentcore-payments/GA announcement: https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-payments-is-now-generally-available-enabling-agents-to-transact-safely-and-autonomously-at-scale/译AgentCore Payments 正式 GA。OpenClaw 智能体可使用 @awscloud 的 aws-agents-pay 插件，在人工批准和额度受限的前提下，为付费 API、MCP 服务器和网络内容完成支付。官方提供了 OpenClaw 操作指南和 GA 公告两篇博客链接。
智能体MCP/工具产品更新
Rohan Paul@rohanpaul_ai23:40
AI 评分 56/100
Zite 推出 MCP，让 Claude、ChatGPT、Cursor 直接构建并上线团队应用Zite's MCP launch deserves a closer look than the usual builder-connects-to-Claude news.Gives Claude, ChatGPT, and Cursor a workspace to create and launch apps with databases, team logins, and roles.The agent here gets file-level tools in a cloud sandbox: read, edit, check, commit, publish, with a database, logins and roles underneath, so what comes back is a running team app, not some code you still have to host.Most builder MCPs forward your prompt to their own agent and bill you credits for it. But here your own Claude, ChatGPT or Cursor does the work, so building uses zero Zite credits on top of the subscription you already pay.The platform provides the environment, your model does the reasoning. imo, thats inversion is very interesting part.译Zite 发布 MCP，把 Claude、ChatGPT 或 Cursor 订阅变成完整 AI 应用构建器，生成的应用自带数据库、团队登录和权限角色。智能体在云端沙箱中获得读取、编辑、检查、提交、发布等文件级工具，产出可直接运行的团队应用。与多数构建器 MCP 把提示词转发给自家代理并收取积分不同，构建工作由用户自己的模型完成，不消耗 Zite 积分。

Dominic Whyte: Today we’re turning your Claude subscription into a full AI app builder. Connect Claude, ChatGPT or Cursor to Zite MCP a...

智能体MCP/工具产品更新
elvis@omarsar023:10
AI 评分 48/100
Zite MCP 让 Claude、ChatGPT 和 Cursor 订阅变身完整 AI 应用构建器An agent is only as useful as the environment it can act in.Zite MCP gives Claude, ChatGPT, and Cursor a place to build and publish a working app with a database, team logins, and roles.The build runs on your existing Claude or ChatGPT subscription with zero Zite credits.译Zite 推出 Zite MCP，将 Claude、ChatGPT 或 Cursor 连接后即可要求生成一个应用，上线即自带数据库、全团队登录和权限角色分配。构建过程使用用户现有的 Claude 或 ChatGPT 订阅，零 Zite 积分。作者评论称智能体的有用程度取决于它能行动的环境。

Dominic Whyte: Today we’re turning your Claude subscription into a full AI app builder. Connect Claude, ChatGPT or Cursor to Zite MCP a...

智能体MCP/工具产品更新
OpenClaw🦞@openclaw11:28
AI 评分 49/100
OpenClaw 播客第九期：创始人团队解读 OpenClaw 2.0Inside OpenClaw 2.0 🦞OpenClaw founder @steipete joins @Pat_Erichsen, @hrudolph and @jlehman_ to discuss the rebuilt Control UI, multiplayer collaboration, stability work, dashboards, memory, skills, and worker nodes.https://openclaw.ai/podcast/episode-9译OpenClaw 发布播客第九期，创始人 @steipete 与 @Pat_Erichsen、@hrudolph、@jlehman_ 讨论 OpenClaw 2.0。内容涉及重构的 Control UI、多人协作、稳定性工作、仪表盘、记忆、技能和 worker 节点。
智能体MCP/工具现象/趋势
jason@jxnlco10:57
AI 评分 61/100
网站可通过 webMCP 在 ChatGPT 桌面应用中直接提供工具给 ChatGPT 和 Codexwebsites can give chatgpt work + codex tools directly through webmcp.on supported accounts, open a supported site in the desktop app’s built-in browser. the address-bar arrow shows its tools. no separate connection needed.https://help.openai.com/en/articles/20001423-using-site-tools-in-the-chatgpt-desktop-app译网站可以通过 webMCP 直接向 ChatGPT 和 Codex 提供工具。在受支持的账号下，在 ChatGPT 桌面应用的内置浏览器中打开受支持的网站，地址栏的箭头会显示该网站的工具，无需单独建立连接。原文附 OpenAI 帮助文档链接 https://help.openai.com/en/articles/20001423-using-site-tools-in-the-chatgpt-desktop-app。
智能体MCP/工具OpenAI产品更新
OpenAI Developers@OpenAIDevs04:15
AI 评分 21/100
OpenAI WebMCP Challenge 距提交截止仅剩 24 小时24 hours.Time to ship your project for the WebMCP Challenge.Entries close tomorrow, Sept 3 @ 1 pm PT.https://openai.com/webmcp-challenge/译OpenAI Developers 提醒 WebMCP Challenge 提交仅剩 24 小时，作品须在 9 月 3 日下午 1 点（太平洋时间）前提交。详情见 https://openai.com/webmcp-challenge/。
MCP/工具OpenAI行业动态
Replit ⠕@Replit02:37
AI 评分 44/100
Replit 团队将直播深入介绍 Replit MCP，支持从 ChatGPT、Claude、Slack 管理 Replit 应用Meet the team behind the Replit MCP this Friday at 9AM PT.Join the Replit community team live with Amadeo Pellicce (@amapel) and Jean-Luc Thumm (@jeanlucthumm) for a deeper dive on the Replit MCP, now live so you can create and manage your Replit apps from ChatGPT, Claude, Slack, or any MCP client.Also joining, our Designathon winner Dino Digi (@dino_digi_llc) on The Dictionary of Invisible Feelings — an interactive companion to their illustrated book that names a feeling you can't, and invents a word when none fits.Live on YouTube, Linkedin and X. RSVP: https://luma.com/04v1q0yj译Replit 宣布本周五上午 9 点（太平洋时间）直播，团队 Amadeo Pellicce 和 Jean-Luc Thumm 将深入介绍 Replit MCP，该功能已上线，用户可从 ChatGPT、Claude、Slack 或任何 MCP 客户端创建和管理 Replit 应用。
智能体MCP/工具产品更新
eric zakariasson@ericzakariasson02:24
AI 评分 35/100
use any model in grok bot！ omnibot maps intents to cursor models once， then routes each ask through…use any model in grok bot!omnibot maps intents to cursor models once, then routes each ask through the cursor clirun /setup-omnibot: browser sign-in or api key, then your intent -> model table. after that you just chat!https://x.ai/bot/OzZrG8ek4AhutfTVhBCI0
智能体MCP/工具开源/仓库

9月2日9月2日周三

星期三 · 4 条
Runway@runwayml23:01
AI 评分 36/100
Runway 发布 Dev MCP，可在编码智能体内连接 Runway 开发者平台Introducing Runway Dev MCP.Connect to the Runway developer platform from inside your coding agent to build, debug and manage. Set up Model Routers, lookup tasks, and more all without leaving your agent. Start building at the link below.译Runway 发布 Runway Dev MCP，让开发者在自己的编码智能体内连接 Runway 开发者平台进行构建、调试和管理。支持设置 Model Routers、查询任务等操作，无需离开智能体。
MCP/工具产品更新编码
OpenBMB@OpenBMB21:07
AI 评分 42/100
OpenBMB 展示基于 MiniCPM5-1B 和 PilotDeck 的开源 Document Field Agent 文档处理工作流📄 What if AI could make document processing smarter and easier? 🥰Developer @Er2Q8UcD6X92167 built Document Field Agent, an open-source document processing workflow that combines models to turn local PDFs, images, and scanned documents into structured, reviewable results.✨ Highlights: ⚡ Powered by MiniCPM5-1B for local document field extraction and intelligent field-level decisions 🤖 Agent-powered workflow with PilotDeck for document task orchestration and MCP integration 📑 OCR + field extraction for documents such as contracts, forms, records, and invoices 🔍 Confidence-based review to flag missing or low-confidence fields for human verificationIt’s exciting to see PilotDeck and MiniCPM5-1B working together in a practical document automation workflow, enabling developers to build more capable and privacy-friendly AI agents. 🙌🔗 Try it: http://github.com/BHD110/document-field-agent🧩 Agent Productivity Platform: http://github.com/OpenBMB/PilotDeck🤗 Model: http://huggingface.co/openbmb/MiniCPM5-1B译开发者基于面壁智能 OpenBMB 的 MiniCPM5-1B 和 PilotDeck 构建了开源项目 Document Field Agent，可将本地 PDF、图片和扫描文档转为结构化、可复核的结果。
智能体MCP/工具开源/仓库
Kling AI@Kling_ai11:59
AI 评分 41/100
可灵 Kling 教程：用 Kling MCP 的 Elements 保持跨镜头角色一致性In this tutorial, learn how to use Elements in Kling MCP to maintain character identity across different shots and create more cohesive AI-generated stories. ✨译可灵 Kling AI 发布教程，讲解如何在 Kling MCP 中使用 Elements 功能，在不同镜头间保持角色身份一致，从而创作更连贯的 AI 生成故事。
MCP/工具教程/实践视频
OpenClaw🦞@openclaw06:28
AI 评分 50/100
OpenClaw Nodes 让智能体远程访问任意设备OpenClaw Nodes let your agent reach devices anywhere.译OpenClaw 官方宣布 Nodes 功能，让用户的智能体可以连接并操作任意位置的设备。配图聊天演示显示，智能体通过 MacBook node 访问本地 Brother MFC-L2690DW 打印机，报告其状态为闲置、队列 0、黑色墨粉约 40%，并调用 imagegen skill 为用户生成适合打印的 "I love you" 图像。

Josh Lehman: openclaw nodes are great

智能体MCP/工具产品更新
已加载 40 条