MCP App StoreLe meilleur de l'écosystème IA et MCP, sélectionné chaque jour.
Sources
Anthropic surveyed 500+ technical leaders to understand how enterprises are actually deploying AI agents — 80% already report measurable ROI. The report covers common deployment patterns, key blockers (trust, evaluation, orchestration), and where agent investment is concentrated in 2026. Useful benchmark data for teams making the case for agent infrastructure internally.
Hugging Face releases swift-huggingface, a comprehensive Swift client for integrating HF models and datasets into Apple ecosystem apps. This enables native AI integration for iOS and macOS developers.
Intel introduces DeepMath, a lightweight math-reasoning agent built using the smolagents framework. It demonstrates efficient agentic workflows for solving complex mathematical problems with minimal overhead.
Hugging Face demonstrates using Claude to fine-tune open-source LLMs, automating the process of creating high-quality synthetic data for training. This highlights the power of frontier models in improving the open-source ecosystem.
OpenAI researchers are exploring 'confessions' as a method to train models to admit mistakes. This approach aims to enhance AI honesty and transparency, potentially reducing hallucinations in production environments.
The release of Transformers v5 introduces simplified model definitions and improved efficiency for the AI ecosystem. These changes streamline how developers implement and scale state-of-the-art models.
MCP Specification Enhancement Proposals (SEPs) are moving from GitHub Issues to pull requests against the `seps/` directory, making proposals easier to review, version, and track. The post explains the rationale and what changes for contributors submitting new SEPs. Relevant for anyone participating in MCP spec development.
Anthropic outlines architectural patterns for building agent harnesses that remain reliable over extended runs — covering context management, checkpointing, graceful error recovery, and how to structure prompts so agents stay on track through dozens of tool calls. Drawn from experience building Claude Code and internal research agents. Pairs well with their later harness design post.
MCP marks its first anniversary with a retrospective on the year and a full breakdown of the November 2025 spec release — the most significant update since launch. Covers new primitives, transport changes, and the governance evolution that brought MCP to production at companies large and small. The canonical reference for what changed in the 2025-11-25 spec version.
Hugging Face's Diffusers library now supports FLUX-2, expanding the ecosystem's capabilities for high-quality image generation. This integration allows developers to more easily implement and fine-tune the latest FLUX models.
A deep dive into the mechanics of continuous batching for LLM inference. This technical explanation is crucial for developers looking to optimize throughput and reduce latency in production AI deployments.
JetBrains is integrating GPT-5 across its IDEs and coding tools. This enables deeper reasoning and architectural design capabilities directly within the developer's workflow.
Tavily details the development of their Deep Research capabilities, explaining the architectural choices used to achieve state-of-the-art results in automated research. Essential reading for developers building agentic search and synthesis workflows.
Anthropic launched advanced tool use capabilities on the Claude API — enabling agents to dynamically discover, learn, and execute tools at runtime rather than having a fixed toolset hardcoded at startup. This allows more flexible agent architectures where Claude can adapt its tool usage based on task context. A significant API capability upgrade for developers building production agents.
OpenAI breaks down what separates good ChatGPT apps from great ones — focusing on how to design capabilities that genuinely improve conversations rather than just adding features. Covers UX principles, capability scoping, and common pitfalls from the ChatGPT Apps SDK team. Practical guidance for anyone building on the Apps SDK.
OpenAI showcases GPT-5's capabilities in solving complex optimization theory problems in collaboration with UCLA. This highlights the model's evolving role in accelerating formal mathematical research and discovery.
The original proposal for MCP Apps (SEP-1865) — introducing a standardised extension for interactive UIs in MCP, developed jointly with the MCP-UI team, OpenAI, and Anthropic. Explains the motivation, design decisions, and how the extension fits within the broader MCP extension model. The precursor post to the January 2026 official launch.
The MCP Bundle format (.mcpb) is now an official part of the MCP project — a portable package format for local MCP servers that enables one-click installation across any compatible client. Addresses the friction of manual JSON config setup and makes MCP server distribution more like installing a regular app.
RapidFire AI significantly accelerates TRL fine-tuning, achieving up to 20x faster training speeds. This allows developers to iterate on model alignment and fine-tuning much more rapidly.
A new unified API for Apple platforms that simplifies switching between local and remote LLMs. This streamlines developer workflows for building cross-platform AI applications on macOS and iOS.