Search stories, models, companies…
Subscribe

Popular topics

OpenAI83Anthropic81Google Gemini45Claude Code27Coding agents51Model Context Protocol (MCP)13
The week in AI, in one email.
Topic · Standard

Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools and data. Anthropic introduced it in November 2024; a year later it was donated to a Linux Foundation-hosted foundation, and it is now supported across most major AI assistants and coding agents.

13 stories · updated Oct 29
Follow via RSSGet Model Context Protocol (MCP) alerts

Key facts

Checked Oct 9
Message format
JSON-RPC 2.0
Current spec version
2026-07-28

Start here

Agents · ExplainerWhat is MCP? The Model Context Protocol explained (2026 edition)MCP is the open standard that lets AI apps plug into tools and data. Here's how it works, who governs it, what changed in the stateless 2026-07-28 spec, and where the risks are.·9 min read
Developers · GuideBuild a local MCP server with the official TypeScript SDK (v2): one tool, one resource, one promptA step-by-step guide to a stdio MCP server using @modelcontextprotocol/server 2.3.1, with code we compiled and ran to check it works, plus the MCP Inspector, Claude Desktop and Claude Code.·5 min read
Developers · ExplainerMCP resources vs tools vs prompts: who decides, and when to use eachMCP servers expose three primitives with three different owners: the model, the app and the user. Here's how each works on the wire in the 2026-07-28 spec, plus what happened to sampling, roots and elicitation.·6 min read

Latest on Model Context Protocol (MCP)

Developers · NewsMLflow RCE CVE-2026-116692 (CVSS 9.8), Google's MCP Toolbox file-exfiltration flaw and a critical LiteLLM advisory: which versions fix themThe MLflow RCE CVE, CVE-2026-116692, is a CVSS 9.8 flaw in third-party scorer loading, fixed in MLflow 3.17.0. It was published on October 27, 2026, a day after Google's CVE-2026-93328 for MCP Toolbox for Databases and alongside a CVSS 10.0 LiteLLM Enterprise advisory. Affected and fixed versions for all three.·7 min readAgents · NewsAgentic AI Foundation adds Agent Skills, Open Responses, OpenEnv and OpenSandbox: what each project is and who donated itThe Agentic AI Foundation took in four new projects on October 22, 2026: Anthropic's Agent Skills, OpenAI's Open Responses, Hugging Face's OpenEnv and Alibaba's OpenSandbox. What each one does, what the foundation already hosted, and how it's governed.·4 min readDevelopers · NewsOpenCode 2.0: one background service for terminal, web and desktop, plus background subagents. What it changes for securityOpenCode 2.0 runs the open-source coding agent as a single shared background service that its terminal, web and desktop clients all connect to, and adds background subagents and async shell commands. Hacker News commenters say the new model broke their sandboxes; OpenCode's docs say shell commands run with your full user authority.·6 min readAgents · NewsGoogle's Gemini agent: what the "universal agent for work" does, who gets it and what it costsGoogle announced the Gemini agent at Gemini at Work on October 8, 2026. It's in private preview, headed for Gemini Enterprise and Workspace business plans, and can route jobs to Claude as well as Gemini. Here's what is confirmed and what Google hasn't said.·5 min readProducts · GuideHow to use Claude in Google Docs, Sheets and Slides: setup, admin controls and limitsClaude for Google Workspace entered public beta on October 6, 2026, for Pro, Max, Team and Enterprise. How to install the add-on, open the sidebar, use connectors, roll it out as an admin, and what it can't do.·7 min readAgents · ExplainerPrompt injection explained: why AI agents that read web pages, email and documents can be hijacked, and which defenses workPrompt injection lets text an AI agent reads, such as a web page, an email or a README, override what you asked it to do. Why models can't reliably tell instructions from data, the incidents that prove it, and the defenses OWASP, NIST, Google DeepMind, Anthropic and OpenAI say actually reduce the risk.·8 min readAgents · NewsMicrosoft Autopilot and Work IQ: what Copilot's always-on agent does, who can get it, and how it's billedMicrosoft Autopilot is a long-running Copilot agent with its own identity, memory and cloud computer, now in private preview. Work IQ, in preview since September 30, connects Copilot to Dynamics 365 and Power Platform data. What's available as of October 12, 2026, and what it costs.·5 min readDevelopers · NewsOpenAI's Agents API puts the Codex harness behind one endpoint: what developers get, and what they give upIn public beta since September 10, with computer use added September 29. How sessions, sandboxes and approvals work, what it costs, and the catches.·5 min readAgents · AnalysisThe case against unattended agents: what went wrong, and how sandboxing actually worksFrom a deleted production database to poisoned npm releases, documented agent failures share a pattern. Here's what the sandboxes in Claude Code, Codex and Copilot actually enforce.·9 min readDevelopers · GuideBuild your first agent with the Claude Agent SDK (TypeScript, October 2026)Install @anthropic-ai/claude-agent-sdk, call query(), lock down tools and permission modes, add a custom MCP tool and a safety hook, and cap spend. Code type-checked against v0.3.293.·7 min read

Nothing in this format on this page — try another filter or the next page.