All posts tagged: mcp

Claude’s real superpower isn’t code — it’s what happens when you add these MCP servers

Claude’s real superpower isn’t code — it’s what happens when you add these MCP servers

Published by skeptic

Claude can be a genuinely impressive AI tool, especially if you’re considering Claude Code’s capabilities. But apart from writing code and handling daily conversations, it can do much more as soon as you bring the hundreds, if not thousands, of MCP servers available to you. These servers let Claude talk to external tools and even turn it into a shockingly good photo editor if you use it right. MCP, or Model Context Protocol, is an open standard that Anthropic released in late 2024. Think of it as a USB connection for AI: one standardized connection type that lets Claude (or any other AI for that matter) plug into databases, web tools, file systems, design apps, and just about anything else you can imagine. The ecosystem has exploded since, and there are tons of MCP servers that make Claude much more useful than it already is. Related MCP is the tech term you’ll be hearing all year — here’s what it means A new acronym is taking over tech circles. It’s called MCP—and it might just …

200,000 MCP servers expose a command execution flaw that Anthropic calls a feature

200,000 MCP servers expose a command execution flaw that Anthropic calls a feature

Published by skeptic

Anthropic created the Model Context Protocol as the open standard for AI agent-to-tool communication. OpenAI adopted it in March 2025. Google DeepMind followed. Anthropic donated MCP to the Linux Foundation in December 2025. Downloads crossed 150 million. Then four researchers at OX Security found an architectural problem that affects all of them. MCP’s STDIO transport, the default for connecting an AI agent to a local tool, executes any operating system command it receives. No sanitization. No execution boundary between configuration and command. A malicious command returns an error after the command has already run. The developer toolchain raises no flag. OX Security researchers Moshe Siman Tov Bustan, Mustafa Naamnih, Nir Zadok and Roni Bar scanned the ecosystem and found 7,000 servers on public IPs with STDIO transport active — and estimate 200,000 total vulnerable instances extrapolated from that ratio. They confirmed arbitrary command execution on six live production platforms with paying customers. The research produced more than 10 CVEs rated high or critical across LiteLLM, LangFlow, Flowise, Windsurf, Langchain-Chatchat, Bisheng, DocsGPT, GPT Researcher, Agent Zero, …

Manufact raises .3M as MCP becomes the ‘USB-C for AI’ powering ChatGPT and Claude apps

Manufact raises $6.3M as MCP becomes the ‘USB-C for AI’ powering ChatGPT and Claude apps

Published by skeptic

For decades, software companies designed their products for a single type of customer: a human being staring at a screen. Every button, menu, and dashboard existed to translate a person’s intention into a machine’s action. But a small startup based in San Francisco and Zurich believes that era is ending — and that the future belongs to companies that build software not for people, but for the artificial intelligence agents that increasingly act on their behalf. Manufact, a three-person company that emerged from Y Combinator’s Summer 2025 batch, announced in February that it raised $6.3 million in seed funding led by Peak XV, the venture capital firm formerly known as Sequoia Capital India and Southeast Asia, which now manages more than $10 billion in assets. Liquid 2 Ventures, Ritual Capital, Pioneer Fund, and Y Combinator also participated in the round, alongside angel investors including the co-founder and chief operating officer of Supabase. The company’s thesis is deceptively simple and potentially enormous: as AI agents take over more of the work that humans perform inside software …

Enterprise MCP adoption is outpacing security controls

Enterprise MCP adoption is outpacing security controls

Published by skeptic

AI agents now carry more access and more connections to enterprise systems than any other software in the environment. That makes them a bigger attack surface than anything security teams have had to govern before, and the industry doesn’t yet have a framework for it. “If that attack vector gets utilized, it can result in a data breach, or even worse,” said Spiros Xanthos, founder and CEO of Resolve AI, speaking at a recent VentureBeat AI Impact Series event. Traditional security frameworks are built around human interactions. There’s not yet an agreed-upon construct for AI agents that have personas and can work autonomously, noted Jon Aniano, SVP of product and CRM applications at Zendesk, at the same event. Agentic AI is moving faster than enterprises can build guardrails — and Model Context Protocol (MCP), while decreasing integration complexity, is making the problem worse. “Right now it’s an unsolved problem because it’s the wild, wild West,” Aniano said. “We don’t even have a defined technical agent-to-agent protocol that all companies agree on. How do you balance …

Gong launches ‘Mission Andromeda’ with AI sales coaching, chatbot and open MCP connections to rivals

Gong launches ‘Mission Andromeda’ with AI sales coaching, chatbot and open MCP connections to rivals

Published by skeptic

Gong, the revenue intelligence company that has spent a decade turning recorded sales calls into data, today launched what it calls Mission Andromeda — its most ambitious platform release to date, bundling a new AI-powered coaching product, a sales-focused chatbot, unified account management tools, and open interoperability with rival AI systems through the Model Context Protocol. The release arrives at a pivotal moment. The revenue technology market is consolidating at a pace that would have been unthinkable two years ago, and Gong — still a private company with roughly $300 million in annual recurring revenue — finds itself at the center of a category that Gartner only formally defined three months ago. Mission Andromeda is Gong’s answer to a basic question facing every enterprise AI vendor in 2026: Can you move beyond surfacing insights and actually change how people work? “The whole show, Andromeda, is basically a collection of very significant capabilities that take us a huge step forward,” Eilon Reshef, Gong’s co-founder and chief product officer, told VentureBeat in an interview ahead of the …

MCP shipped without authentication. Clawdbot shows why that’s a problem.

MCP shipped without authentication. Clawdbot shows why that’s a problem.

Published by skeptic

Model Context Protocol has a security problem that won’t go away. When VentureBeat first reported on MCP’s vulnerabilities last October, the data was already alarming. Pynt’s research showed that deploying just 10 MCP plug-ins creates a 92% probability of exploitation — with meaningful risk even from a single plug-in. The core flaw hasn’t changed: MCP shipped without mandatory authentication. Authorization frameworks arrived six months after widespread deployment. As Merritt Baer, chief security officer at Enkrypt AI, warned at the time: “MCP is shipping with the same mistake we’ve seen in every major protocol rollout: insecure defaults. If we don’t build authentication and least privilege in from day one, we’ll be cleaning up breaches for the next decade.” Three months later, the cleanup has already begun — and it’s worse than expected. Clawdbot changed the threat model. The viral personal AI assistant that can clear inboxes and write code overnight runs entirely on MCP. Every developer who spun up a Clawdbot on a VPS without reading the security docs just exposed their company to the protocol’s …

Claude Code MCP Upgrade 2026 : Cut Tokens by 95% with Smart Loading

Claude Code MCP Upgrade 2026 : Cut Tokens by 95% with Smart Loading

Published by skeptic

What if you could make your workflows not just faster, but ten times faster? Better Stack outlines how Claude Code’s latest update has transformed Model-Connected Plugin (MCP) functionality, delivering a staggering boost in speed and efficiency. By tackling long-standing challenges like token inefficiency and operational errors, this breakthrough introduces a smarter, leaner way to handle large language models. Imagine cutting token usage by up to 95% while maintaining precision and control, this isn’t just incremental progress; it’s a paradigm shift in how we think about performance and scalability in AI-driven systems. In this deep dive, we’ll explore the two innovative optimization strategies that make this leap possible: search-based selection and programmatic orchestration. Whether you’re intrigued by the simplicity of dynamically loading only the most relevant features or the advanced customization offered by programmatic control, there’s something here to transform how you approach complex workflows. Along the way, you’ll uncover how these updates address critical issues like naming collisions and command injections, paving the way for more secure and efficient applications. The implications are profound, how …

In 2026, AI will move from hype to pragmatism

In 2026, AI will move from hype to pragmatism

Published by skeptic

If 2025 was the year AI got a vibe check, 2026 will be the year the tech gets practical. The focus is already shifting away from building ever-larger language models and toward the harder work of making AI usable. In practice, that involves deploying smaller models where they fit, embedding intelligence into physical devices, and designing systems that integrate cleanly into human workflows.  The experts TechCrunch spoke to see 2026 as a year of transition, one that evolves from brute-force scaling to researching new architectures, from flashy demos to targeted deployments, and from agents that promise autonomy to ones that actually augment how people work.  The party isn’t over, but the industry is starting to sober up. Scaling laws won’t cut it Image Credits:Amazon In 2012, Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton’s ImageNet paper showed how AI systems could “learn” to recognize objects in pictures by looking at millions of examples. The approach was computationally expensive, but made possible with GPUs. The result? A decade of hardcore AI research as scientists worked to invent …