惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 聂微东
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
L
LangChain Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 司徒正美
WordPress大学
WordPress大学
T
The Blog of Author Tim Ferriss
Blog — PlanetScale
Blog — PlanetScale
J
Java Code Geeks
Y
Y Combinator Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
GbyAI
GbyAI
Vercel News
Vercel News
大猫的无限游戏
大猫的无限游戏
T
Tailwind CSS Blog
Jina AI
Jina AI
B
Blog
Recorded Future
Recorded Future
MyScale Blog
MyScale Blog
I
InfoQ
aimingoo的专栏
aimingoo的专栏
博客园_首页
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
雷峰网
雷峰网
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
腾讯CDC
爱范儿
爱范儿
Last Week in AI
Last Week in AI
博客园 - 三生石上(FineUI控件)
博客园 - Franky
Schneier on Security
Schneier on Security
V
V2EX
TaoSecurity Blog
TaoSecurity Blog
H
Hacker News: Front Page
Cloudbric
Cloudbric
D
DataBreaches.Net
B
Blog RSS Feed
P
Palo Alto Networks Blog
云风的 BLOG
云风的 BLOG
NISL@THU
NISL@THU
I
Intezer
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Cyberwarzone
Cyberwarzone
F
Fortinet All Blogs
D
Darknet – Hacking Tools, Hacker News & Cyber Security
C
Cybersecurity and Infrastructure Security Agency CISA
C
Cisco Blogs
K
Kaspersky official blog
Forbes - Security
Forbes - Security

The New Stack | DevOps, Open Source, and Cloud Native News

Agentic development hinges on verification. For cloud-native software, that is a runtime problem. AI agents need infrastructure: Why Europe’s regional cloud strategy matters Transform your AI coding agent into a deterministic Java Spring expert WeAreDevelopers is coming to the US to give unsung developers a bigger voice Cleaner AI training data, fewer bugs: Sonar’s SonarSweep explained Observability overload is drowning engineers Google’s DiffusionGemma is 4x faster than its other Gemma models Fable 5: Guardrails and burn rate are annoying users, who say it’s still better than Opus 4.8 The Anthropic leader who built Claude Code says he ditched prompting — now he just writes loops. AWS can now mathematically prove your VMs are isolated Microsoft pulled 73 GitHub repos after malware attack — but still won’t say who’s compromised Databricks wants to kill the “email me a file” problem for AI agent skills Ramp bets forward deployed engineers can do what off-the-shelf finance AI can’t Git real: AI agents aren’t just for solo developers anymore Anthropic launches Claude Mythos/Fable 5, but you better try it soon This AI agent startup ditched Anthropic for DeepSeek — and says it’s saving millions When your data model is the bottleneck: lessons from Medium’s feature store How long before we stop reading the code? The tokenmaxxing party is over, and Revenium is mopping up How AI is solving the memory crunch it created Microsoft’s pitch to enterprises: Ditch Azure Repos for GitHub, despite its rocky reliability record Claude Code’s biggest upgrade yet ran 5 agents at once — here’s what happened Why Anthropic just doubled Claude Cowork limits at no charge For years, Apache Cassandra handed this work to your team — 6.0 takes it back “A dangerous combination”: The 2 factors that can “corrupt” AI agent workflows With Foundry, Microsoft bets the enterprise AI battle is about reliability, not capability Microsoft unlocks Visual Studio for developers left behind by its own AI AI teams now deploy 1,000 times a month. Your pipeline wasn’t built for that. Microsoft just made the agent runtime free — and kept everything around it “Whoever builds the most joyous product wins”: The agent war begins Netlify CTO Dana Lawson: Writing code is no longer the job From Jupyter Notebook to production: How to ship AI systems that actually work OpenClaw used Gavriel Cohen’s code and exposed the AI Agent accountability problem Replit shows how vibe coding is getting its own financial stack — and a path to profit Cloudflare aqui-hires VoidZero: Did a piece of the open web just stabilize, or become more brittle? Cursor cuts prices and adds enterprise spend controls amid “tokenomics” reckoning Google Gemma 4 12B nearly matches 26B benchmarks — and runs on your laptop Snowflake thinks it knows what’s really slowing developers down Autonomous agents have met their biggest challenge yet: The database. Why agentic AI makes the ops platform the most important layer in the enterprise How to dramatically improve enterprise security alert tuning to battle cyberattacks Why the need for humans won’t disappear in the age of autonomous databases How to secure Kubernetes in the age of AI workloads Asana says its new AI “chief of staff” turns your Slack chaos into trackable work Nvidia’s best model is now live Mate Security’s Asaf Wiener made every backend engineer a model router. He’s right to. The AI cost crisis finally has a watchdog — just not the companies causing it How to get operational data off the factory floor without creating an IT breach Why CPUs still matter in the age of AI agents Rayfin: Microsoft’s answer to the gap between vibe coding and enterprise production Microsoft bets the enterprise AI race will be won on data context, not model power “A successful attack could be catastrophic”: Anthropic gives more groups access to Claude Mythos How GitHub plans to win developers back Microsoft really, really, really wants developers to love Windows again With Intelligent Terminal, Microsoft is reinventing the Windows terminal Microsoft debuts “Scout” at Build, a new personal agent for work OpenAI’s Codex adds new tools — Sites, Annotations, more plugins — for knowledge workers GitHub Copilot’s usage-based billing is live: Here’s what you need to know OpenAI, Anthropic, Google, Amazon, and xAI all fail on type of attack, study finds JetBrains open-sources Mellum2 to go where Claude Code can’t Claude Code vs. Cursor vs. Codex vs. Antigravity — six months in This coding agent doesn’t want your feedback — it ships without it “Blowing things up”: The one move vendors got wrong on AI agents At Sapphire, SAP makes the case that enterprise AI is a context problem Gavriel Cohen found his own code inside OpenClaw, so he walked away AI retrieval at scale is becoming a systems problem, not a tooling problem The DIY platform trap that’s burning out engineering teams I tested Cursor’s new Jira integration and it’s 5 stars, no notes. Here’s why. Why GPT-5.4, Claude, and Gemini can’t agree on basic, real-world facts Replit’s vibe coding platform just got a Visa-backed identity layer for AI agents — and it changes how agents spend money Opus 4.8 Made Claude Smarter. Token Discipline Got Urgent. Why Linux creator Linus Torvalds gets angry hearing “99% of code is AI” Vendor neutrality isn’t magic: A hard look at the OpenTelemetry ecosystem “The AI did it” won’t save you when EU regulators come knocking The fix for soaring AI cloud bills exists — so why won’t we trust it? AI is shipping code faster than security was built to handle Why AWS scrapped OpenSearch’s architecture to chase agent workloads Claude Opus 4.8 is here: effort controls, dynamic workflows, cheaper fast mode, better honesty, less deception Percona celebrates 20th birthday with new foundation — and a goat cake Why OpenAI and Anthropic are hiring forward deployed engineer teams Claw-style AI agents are coming to the enterprise. The governance infrastructure is still catching up. The agentic identity crisis: Why your security isn’t ready for the AI revolution Debugging the undebuggable: building observability into probabilistic AI systems Snowflake commits $6B to AWS as it pushes deeper into AI Why MotherDuck refuses to fork DuckDB Researcher “gave Claude Code ‘ADHD’… and it thinks 2x better now.” Outside experts want more proof. “There is no accountability”: AI coding agents are installing packages no one owns “Tokenmaxxing is real, expensive & it’s spreading”: AI budgets are exploding With Google’s debut, the most important AI agent feature is now the most boring one Why AI agents need a Context Lake Google ranks the best AI for building Android apps, and the winner isn’t Gemini Google pushes Pro, Ultra, and free users from open-source Gemini CLI to closed-source Antigravity CLI The reason enterprise outages almost never start where ops teams think Taming the agentic influx: a blueprint for AI business observability How the AC/DC framework helps teams govern AI coding agents GitLab 19.0 trades its string section for a full DevSecOps orchestra Who’s monitoring the agents? How Jaeger hit 8.6× compression on 10 million spans with ClickHouse What ClickHouse learned from a year of coding with AI agents OpenClaw passed 300,000 GitHub stars. Then Google launched Spark.
MCP gets its missing enterprise authorization layer
Frederic Lardinois · 2026-06-19 · via The New Stack | DevOps, Open Source, and Cloud Native News

Every enterprise company is seemingly trying to adopt the Model Context Protocol (MCP) to connect its AI agents to tools. But so far, authorizing those connections has meant employees clicking through an OAuth prompt for every server. For a while now, the MCP project has been working on the “Enterprise-Managed Authorization” extension, with the goal of allowing enterprises to control MCP server access centrally through their existing identity provider.

This extension is now stable and Anthropic and Microsoft are among the first to support it in their clients, including Claude, Claude Code, Claude Cowork, and Visual Studio Code, with Okta as the first identity provider.

After its launch, MCP quickly grew organically, but as is so often the case, the original spec wasn’t designed for enterprise use cases. The standard MCP authorization model was built for individuals. Authorizing servers, even today, means connecting service after service by hand, but this also means security teams can’t enforce consistent policy or keep a single audit trail — and there is always the risk of an employee connecting a personal account to a work tool.

“Logging in once and automatically having all your MCP connectors automatically set up is pretty magical,” says Tom Moor, the Head of Engineering at Linear, in today’s announcement.

The token handoff

Enterprise-Managed Authorization makes the identity provider the decision-maker for which servers a client can reach. An administrator sets the policy once, and employees sign in with the corporate identity they already use.

Unlike with OAuth, the exchange runs without a consent screen. During single sign-on, the client obtains a signed assertion from the identity provider that vouches for both the user and the application requesting access. It then presents that assertion to the MCP server’s own authorization server, which returns a scoped access token the client can then use to make its calls.

That assertion is actually an emerging OAuth extension called the Identity Assertion JWT Authorization Grant, or ID-JAG, now an IETF draft. Okta’s branded version is Cross App Access. Because ID-JAG is an open standard, any identity provider could implement it, though Okta is the only one to have shipped support so far.

Giving control back to IT

Credit: MCP

For an IT team, this ideally means an end to the inevitable sprawl of individual approvals. Now, an admin can enable a server for the organization (or specific teams or even individuals), and employees and their agents inherit access to it, scoped to the groups and roles they already hold.

Control and audit move into the identity provider’s console. Access decisions leave one trail across every connector, and revocation runs the same path as everything else, so deactivating a user cuts their MCP access at the same time.

Since corporate IT now controls this connection, mixing and matching personal and work accounts — whether by accident or on purpose — becomes much harder.

In practice, this looks like Anthropic’s and Okta’s implementation, which means Claude Managed Agents can now also be imported into the corporate directory and treated as identities with human owners, while a compliance interface feeds risk signals like dormant agents or misconfigured accounts back to security teams.

Identity, not authorization

In today’s announcement, Aaron Parecki, Okta’s director of identity standards, calls the result making the identity provider “a centralized governance plane” for MCP access. That governance plane decides who connects to what. It does not decide whether a given action is allowed, though.

It’s worth noting that the permissions the extension hands over are broad. Whether a particular agent should be allowed to run a specific action on a specific resource at a given moment is a decision that is managed by the policy engines and gateways that now typically sit between an agent and the tools it calls.

What’s next

Beyond Anthropic, Okta and Microsoft, companies like Asana, Atlassian, Canva, Figma, Granola, Linear, and Supabase now support the extension. Slack and a number of other companies will soon add support, too.

Okta is also bringing native support for the protocol to its Auth0 developer platform, letting developers expose their MCP servers without implementing it from scratch.

YOUTUBE.COM/THENEWSTACK

Tech moves fast, don't miss an episode. Subscribe to our YouTube channel to stream all our podcasts, interviews, demos, and more.

Created with Sketch.