Le meilleur de l'écosystème IA et MCP, sélectionné chaque jour.
Sources
Anthropic shares practical techniques for managing what goes into an agent's context window — what to include, what to summarise, what to drop, and how to structure information so agents reason more reliably. Context engineering is increasingly recognised as a core skill for agent developers, and this is one of the clearest practical guides on the topic.
The MCP team shares timelines and priorities for the next spec version — covering what features are slated, what's been deferred, and how the community can influence what gets included. Useful context for developers planning integrations or building on features that depend on upcoming spec changes.
OpenAI explains the design rationale behind the Responses API — how it unlocks persistent reasoning, hosted tools, and multimodal workflows that the Chat Completions API couldn't cleanly support. The post covers the architectural decisions and use cases it was designed to enable for GPT-5. The canonical reference for understanding why the Responses API exists.
Anthropic published a transparent technical postmortem on three bugs that intermittently degraded Claude's responses — explaining what happened, why each took time to diagnose and fix, and what engineering changes resulted. Rare public transparency from an AI lab on production reliability issues. Useful reading for teams thinking about AI system reliability.
OpenAI's engineering notes on recent Realtime API updates — covering improvements to speech-to-speech latency, turn detection, interruption handling, and session management. Targeted at developers already building with the Realtime API who want to understand the subtle behaviour changes in recent model snapshots.
Anthropic used Claude agents to help design and iterate on tool definitions for other agents — effectively dog-fooding agent tooling. The post covers what makes a tool definition good (clear name, typed params, explicit error cases) and how using agents to write tools surfaces issues that humans miss. Meta but practical.
The MCP Registry launched in preview — an open catalog and API for discovering publicly available MCP servers. Provides a standardised way for clients to discover servers, check metadata, and verify compatibility without relying on community-maintained lists. The infrastructure layer that makes the MCP ecosystem more navigable as it grows.
The official PHP SDK for MCP is now generally available, built in collaboration with the PHP Foundation and Symfony. Brings idiomatic PHP support to MCP server development, opening the protocol to the large PHP developer community. Part of MCP's push to have official SDKs across all major languages.
Anthropic is piloting a native Claude integration inside Chrome, bringing AI assistance directly into the browser without switching tabs or apps. The pilot explores how Claude can help with web research, form-filling, summarisation, and contextual tasks as users browse. An early look at where browser-native AI assistance is heading.
A deep dive into how MCP handles OAuth 2.1 client registration — the mechanism that lets MCP clients and servers establish trust without a pre-existing relationship. Explains the two core challenges (dynamic registration, trust bootstrapping) and the design choices made to solve them in a way that scales to the open MCP ecosystem. Essential for developers building MCP clients or auth-enabled servers.
A practical tutorial on using MCP prompts and resource templates to build workflow automation — walking through a meal planning example that demonstrates how prompts can chain resources and tools into reusable, composable workflows. Prompts are an underused MCP primitive and this is one of the clearest guides to their practical value.
The MCP project introduced its formal governance model: Specification Enhancement Proposals (SEPs), a defined maintainer structure, and a community-driven process for evolving the protocol. This post marked MCP's transition from an Anthropic-led project to a community-governed open standard, laying the groundwork for the later Linux Foundation donation.
A behind-the-scenes look at how Anthropic’s own teams use Claude Code day-to-day: debugging production issues, navigating unfamiliar codebases, building internal automation tools, and accelerating code review. The post doubles as a practical guide with real patterns teams have found most effective. Worth reading for anyone trying to get more from Claude Code.
Anthropic launched Desktop Extensions — a one-click installation system for MCP servers directly in Claude Desktop, eliminating the need to manually edit JSON config files. Users can browse, install, and manage MCP servers from a UI without touching the terminal. A major UX improvement that significantly lowers the barrier to MCP adoption.
Anthropic walks through the engineering decisions behind Claude's Research feature — a multi-agent system that parallelises web search, synthesises findings across agents, and produces long-form research reports. The post covers orchestration architecture, reliability challenges, and how they handled conflicting information between sub-agents. Valuable real-world reference for anyone building research or RAG-style multi-agent systems.
Anthropic launched integrations allowing Claude to connect directly to external tools and services — an early milestone in Claude’s MCP-powered ecosystem. Users can connect Claude to apps, databases, and APIs so it can take actions and retrieve live context rather than working only from conversation input. This laid the groundwork for the MCP integration ecosystem.
Anthropic's official best practices guide for Claude Code — covering how to structure tasks, write effective CLAUDE.md files, use tools efficiently, manage context, and get reliable results on complex coding tasks. The canonical reference for getting the most out of Claude Code in production. Should be required reading before any serious Claude Code deployment.
Anthropic introduced a dedicated "think" tool that gives Claude a scratchpad to reason through complex multi-step tool use situations before acting. In tests, adding the think tool significantly improved accuracy on tasks requiring careful sequencing of tool calls. A simple but effective technique any agent developer can adopt immediately.
Anthropic achieved then-state-of-the-art performance on SWE-bench Verified with Claude 3.5 Sonnet using only a bash tool and a text editor — no scaffolding tricks. The post details the technical approach and what the benchmark results imply about real-world software engineering capability. A landmark result that established Claude as a serious coding model.
Anthropic's foundational guide to building reliable AI agents — covering when to use agents vs. simpler pipelines, how to design tool interfaces, how to handle failures gracefully, and the core patterns (augmented LLM, routing, parallelisation, orchestrator-subagent) that underpin most production agent systems. Still one of the best starting points for anyone new to agent development.
