#MCP
502 related articles
Anthropic Open-Sources sandbox-runtime: A Container-Free Sandbox for AI Agents
Anthropic open-sources sandbox-runtime (srt), an OS-level sandbox built on macOS Seatbelt and Linux bubblewrap that restricts file and network access for AI agents, MCP servers, and CLI tools—lightweight isolation without containers.
DB Chat: Conversing with PostgreSQL in Natural Language, with AI Auto-Generating SQL
dbchat lets users converse with a PostgreSQL database in natural language, with an AI agent auto-generating SQL and returning live results. This article analyzes its MCP Server + Next.js + AWS full-stack architecture and anti-hallucination guardrail design.
Building AI Agents with Python and the Claude API: Tool Use and MCP in Practice
A hands-on Python AI Agent tutorial with the Claude API: from basic messages.create calls to Tool Use, Agent Loop implementation, the MCP open standard, the Claude Agent SDK, and security best practices.
Gemini CLI's Seven Key Features: A Million-Token Open-Source Terminal AI Agent
What is Gemini CLI? Discover its seven key features: Apache 2.0 open source and free, 1M token context, MCP integration, GEMINI.md configuration, slash commands, and Google Search grounding, plus getting-started advice.
Sidekick: One MCP Server Connects Alexa, AI Agents, and Voice Games
Amazon Hackathon project Sidekick uses one MCP server to power Alexa-style voice, AI agents, and voice games; Control Room logs the full request chain, and Movie Buddy grounds answers with subtitle cues.
Claude Agent Tool Integration Guide: Custom Tools, MCP, and Subagents
An in-depth look at Claude agent tool integration: custom tool definitions, MCP server access, tool search, and subagent budget control for production-grade agent systems.
How MCP Makes Wi-Fi AI Agents Practical: From the Plumber Analogy to a 15-Minute Build
A WLPC Prague 2026 talk breakdown: how MCP lets AI agents connect to Wi-Fi networks, the full 15-minute process for building your first MCP server, and the four hard rules for tool design—read-only by default, credential isolation, and audit logging.
AI Agent Security Field Manual: Defending Against Injection, MCP Poisoning, and Zero-Click Leaks
AI Agent security field guide: from the lethal trifecta and prompt injection principles, with six real cases (Copilot zero-click leak, Slack AI, MCP poisoning, malicious NPM package, Glassworm invisible characters, OAuth supply chain attack), nine layers of defense controls (least privilege, sandboxing, default deny, egress monitoring), three-tier implementation roadmaps for individuals, teams, and enterprises, and a first-hour incident response checklist.
Andrew Ng Teams Up with Anthropic: A Complete Walkthrough of the Claude Code Hands-On Tutorial
Andrew Ng and Anthropic launch a Claude Code short course covering clear context, parallel sessions, MCP servers, and three hands-on projects: a RAG chatbot, Jupyter data analysis, and Figma-to-frontend.
How Does an AI Agent Control Your Computer? A Full Breakdown of Hermes' Three-Layer Toolchain
Bilibili creator Xiaoyou breaks down Hermes' three-layer toolchain for operating a computer: the built-in Terminal, file modification, and code execution foundation; optional web search, vision analysis, speech synthesis, and browser/desktop control; and an external ecosystem freely extended via CLI and MCP—plus why SSH connects but still can't operate.
MCP and Zero Trust: Verifying Every AI Agent Tool Call
Mapping NIST's seven zero trust principles to the MCP request path, analyzing which capabilities the spec provides versus what must be built for AI agent tool calls, and listing five verification checks every call should pass.
Reverse Engineering + AI Agents: The T…
Reverse Engineering + AI Agents: The Technical Truth Behind Cloning Adobe Apps in Weeks
A developer used AI Coding Agents for reverse engineering to build 7 open-source Adobe alternatives in weeks. We explore how it works, the MCP Server that hit 100K stars in 6 days, and the real technical and legal limits.
New in Notion 3.8: Your ChatGPT Subscription Now Works Directly in Notion Agent
Notion 3.8 lets Business/Enterprise workspaces connect ChatGPT Plus, Pro, or Go subscriptions to power Notion Agent, replacing Notion credits. Eligibility, setup, MCP risks, and team implications explained.
Claude Security Upgrades Continuous Scanning: Automatic Fix Tracking and API Integration
Claude Security adds continuous scanning: re-scan on commit, auto-resolve fixed findings, plus API, MCP connectors, and Webhooks. Integration, limits, and cost explained.
The Essential Difference Between Chatbots and AI Agents: Crossing from Conversation to Execution
What's the difference between a chatbot and an AI agent? Based on the MCP series on the Learn Tech channel, this article uses examples like booking flights and summarizing notes to explain: a chatbot only gives answers, while an agent actually completes tasks through a think-act-observe loop. It breaks down the four core components—model, tools, memory, and goal—as well as MCP's role as a bridge, and discusses agents' applicable boundaries and permission risks.
AI Agent Tool Permissions Out of Control? Citadel Identity360 Governs Them with an MCP Registry
How does Citadel Identity360 govern AI Agent tool access? It discovers Agents across platforms, binds human owners, builds an MCP registry to visualize access paths, and enforces tool-level authorization with OAuth gating and function whitelists to close Agent permission blind spots.
Complete Guide to Connecting Cursor AI to the GitHub MCP Server
A step-by-step guide to connecting Cursor AI to the GitHub MCP server: create a personal access token, configure mcp.json, store the token in the ENV block, and verify with a PR query.
WorkBuddy Beginner's Guide: A Full Breakdown of Desktop AI Agents and MCP Configuration
WorkBuddy desktop AI agent beginner's guide: its core capabilities, differences from CodeX, three major misconceptions, and the MCP configuration and Expert Center learning path to help office workers transform from AI question-askers into AI managers.
Amazon Blocks AI Agents While Walmart Opens Its Doors: The Battle for the Retail Front Door
Amazon blocks AI shopping agents in court and at the firewall, while Walmart opens access via an official MCP server. We analyze both strategies and what developers should do.
AgentCore in Practice: Connecting Custom Tools and MCP Servers to Agents
DebuggerCafe tutorial shows how to connect custom tools and MCP servers to Amazon Bedrock AgentCore agents, covering tool contract design, MCP reuse, and production concerns.