Tag
Google launches Gemini Spark, an always-on AI agent powered by Gemini 3.5 Flash, with background operation, integrations across Workspace and third-party apps via MCP, and updates to Antigravity.
A developer built a Model Context Protocol (MCP) index containing 3 million arXiv papers to help LLMs retrieve accurate research citations and reduce hallucinations, and is now seeking testers for feedback.
This paper presents NIMO Controller, a self-driving laboratory orchestrator based on the Model Context Protocol (MCP), which provides a unified interface for both human users and AI agents through a visual programming interface and MCP-based tool discovery.
The author describes a common user onboarding problem with MCP servers—users opening the endpoint in a browser and seeing a 401 error—and shares a simple hack: returning an HTML page that explains how to properly add the server to an LLM client, which drastically reduced support tickets.
A defense of MCP (Model Context Protocol) against criticism that it puts garbage in context, noting that modern tools like Claude Code, Codex, and Cursor implement progressive disclosure and load MCP tools on demand, making the complaint outdated. The author argues MCP is best for cloud-hosted platforms requiring authentication and discoverability.
OpenAI introduces a new generation of apps in ChatGPT with an open-source Apps SDK built on the Model Context Protocol, allowing developers to reach 800+ million users. Initial partner apps from Booking.com, Canva, Coursera, Figma, Expedia, Spotify, and Zillow are available today with more launching later this year.
The Model Context Protocol (MCP) reference servers repository collects official reference implementations demonstrating MCP features and SDK usage, including Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking, and Time servers, alongside links to community servers and the MCP Registry.
This article presents a curated list of awesome Model Context Protocol (MCP) servers, providing a web directory for AI models to interact with local and remote resources through standardized server implementations.
FastMCP is a Python framework by Prefect for building MCP servers, clients, and apps, simplifying the connection of LLMs to tools and data.
Desktop Commander MCP is an open-source tool that allows AI to search, update, manage files, and run terminal commands via the Model Context Protocol, with enhanced file previews and command execution.
MCP for Unity is an open-source tool that bridges AI assistants with the Unity Editor via Model Context Protocol, providing 47 tool entrypoints for natural language control of scenes, assets, scripts, and workflows.
n8n-MCP is an MCP server that gives AI assistants comprehensive access to n8n's 1,650 workflow automation nodes, enabling them to understand and work with n8n nodes effectively. It provides structured access to node properties, operations, documentation, templates, and community integrations, and can be self-hosted or used via a cloud dashboard.
Anthropic shares engineering best practices for designing, evaluating, and optimizing tools for AI agents, specifically utilizing the Model Context Protocol (MCP) and Claude Code to improve agent performance.
Anthropic publishes a guide defining context engineering as the evolution of prompt engineering, focusing on curating optimal context tokens for AI agents to maintain performance and focus during multi-turn inference.