Best of mcp — March 2026

  1. 1
    Article
    Avatar of thomasthorntonThomas Thornton·6w

    Draw.io MCP for Diagram Generation: Why It’s Worth Using

    Draw.io MCP connects draw.io with AI tools via the Model Context Protocol to generate architecture diagrams from structured text, CSV, or Mermaid input. Instead of manually arranging shapes, engineers can produce a draft .drawio, .png, or .svg file in seconds, commit it to Git, and regenerate it when infrastructure changes. The post covers practical usage patterns including a CI/CD diagram example using a GitHub Copilot skill, tips for keeping automated diagrams readable (3-4 lanes, left-to-right flow, one responsibility per box), and a lightweight team adoption path. The core argument is that diagrams should be version-controlled living assets that evolve with code, not static slide-deck artifacts.

  2. 2
    Article
    Avatar of daily_updatesdaily.dev Changelog·4w

    daily.dev skills are here

    daily.dev launched Skills, a set of plug-and-play integrations that connect AI coding agents to daily.dev's real-time, community-vetted developer content. Three skills are available: daily-dev (personalized feed, bookmarks, search), daily-dev-ask (developer-focused web search grounded in upvoted articles), and daily-dev-agentic (continuous self-improvement via fresh article ingestion). Skills work with Claude Code, Cursor, Codex, and OpenClaw, and require a Plus subscription. Setup takes about 30 seconds via the API settings page.

  3. 3
    Article
    Avatar of storybookStorybook·3w

    Storybook MCP for React

    Storybook MCP is a new Model Context Protocol server for React that gives AI coding agents intelligence about your existing component library. It provides agents with component metadata (stories, API, docs) to reuse existing components instead of generating new patterns, embeds live story previews directly in chat UIs, and enables agents to run component and accessibility tests autonomously — fixing issues or flagging them for human review. Available now in Storybook 10.3 for React, with support for other frameworks coming later. Teams can publish the MCP server remotely via Chromatic to share component context without running Storybook locally.

  4. 4
    Article
    Avatar of bytebytegoByteByteGo·4w

    How Stripe’s Minions Ship 1,300 PRs a Week

    Stripe runs over 1,300 fully automated pull requests per week using internal coding agents called Minions. These unattended agents work without human supervision, spinning up isolated cloud machines in under ten seconds, reading documentation, writing code, running linters, and submitting PRs ready for review. The system works because of four foundational layers: isolated devbox environments built for human engineers long before LLMs existed, hybrid 'blueprint' orchestration that mixes deterministic steps with agentic loops, curated context delivery via scoped rule files and a centralized MCP tool server called Toolshed, and fast feedback loops capped at two CI rounds to avoid diminishing returns. The key insight is that strong developer infrastructure—test suites, isolated environments, fast feedback—is the prerequisite for effective coding agents, not model selection.

  5. 5
    Article
    Avatar of redpandaRedpanda·4w

    Introducing Redpanda AI SDK for Go

    Redpanda has open-sourced an AI SDK for Go designed for production use. The SDK addresses gaps in existing Go AI tooling by providing provider portability across OpenAI, Anthropic, Google Gemini, and AWS Bedrock, idiomatic streaming, composable middleware with layered interceptors, an Agent-to-Agent (A2A) adapter, a flexible tool system with MCP support, and a simulated LLM framework for deterministic testing. It powers Redpanda's own Agentic Data Plane and is available at github.com/redpanda-data/ai-sdk-go.

  6. 6
    Article
    Avatar of ghblogGitHub Blog·5w

    The era of “AI as text” is over. Execution is the new interface.

    GitHub has released the Copilot SDK, which lets developers embed agentic execution capabilities directly into their own applications. Rather than relying on text-in/text-out AI interactions, the SDK exposes the same planning and execution engine that powers GitHub Copilot CLI as a programmable layer. Three key patterns are highlighted: delegating multi-step work to agents instead of brittle scripts, grounding execution in structured runtime context via Model Context Protocol (MCP), and embedding agentic execution outside the IDE into desktop apps, SaaS platforms, background services, and event-driven systems.

  7. 7
    Article
    Avatar of chromeChrome Developers·5w

    When to use WebMCP and MCP

    WebMCP and MCP serve complementary roles in building agentic web experiences. MCP is a universal backend protocol connecting AI agents to external systems, data sources, and workflows across any platform. WebMCP is a proposed browser standard that exposes frontend tools to browser-based agents, giving them structured, reliable access to live website UI, DOM, session data, and cookies. Key differences: MCP is persistent and platform-agnostic; WebMCP is ephemeral and tab-bound. The recommended approach is to use MCP for core business logic and background tasks, and WebMCP for contextual in-browser interactions when a user is actively on your site.

  8. 8
    Article
    Avatar of minersThe Miners·5w

    Figma MCP Builds Exactly What You Ask – Nothing More

    Two developers ran real-world experiments using Figma's MCP with Claude Code to convert Figma designs into code. Key findings: the tool is highly literal and does exactly what you ask — no more. Specificity in prompts is critical; vague requests yield inconsistent results. Visual translation from Figma to code is accurate, but structural best practices (file separation, responsiveness, component organization) must be explicitly requested. Applying changes to an existing codebase works better than greenfield generation because Claude has structural context to follow. A major practical blocker is Figma's MCP quota on the free tier (~6 requests/month), which severely limits experimentation. Design library mapping is also a current weak point.

  9. 9
    Article
    Avatar of chromeChrome Developers·5w

    What's new in DevTools (Chrome 146)

    Chrome 146 DevTools ships several notable updates: the DevTools MCP server reaches v0.19.0 with Lighthouse audit integration, a --slim token-saving mode, new accessibility and LCP debugging skills, memory snapshots, and screencast recording. Console history now preserves edits while navigating between commands. Adopted Style Sheets gain a dedicated DOM node in the Elements panel, enabling direct inspection and editing. The Grid Editor adds dense packing support for grid-auto-flow. The Privacy and Security panel is renamed to Security, with privacy issues consolidated into the Console. Stack trace architecture in Sources was overhauled to fix source map jumping issues.

  10. 10
    Article
    Avatar of aspnetASP.NET Blog·6w

    Release v1.0 of the official MCP C# SDK

    The Model Context Protocol (MCP) C# SDK has reached v1.0, implementing the 2025-11-25 MCP Specification. Key additions include: enhanced OAuth authorization server discovery with three PRM exposure methods; icon metadata for tools, resources, and prompts; incremental scope consent following the principle of least privilege; URL mode elicitation for secure out-of-band user interactions; tool calling support within LLM sampling requests using Microsoft.Extensions.AI; OAuth Client ID Metadata Documents (CIMD) as a preferred alternative to Dynamic Client Registration; long-running HTTP request handling via SSE polling with DistributedCacheEventStreamStore; and experimental Tasks support for durable state tracking and deferred result retrieval with lifecycle management.

  11. 11
    Article
    Avatar of on_leuwcqSamuel Adekunle·4w

    Stitch + Antigravity + Flutter: Build Apps with AI Agents in 2026

    A walkthrough of an AI-assisted Flutter app development workflow using Google's Stitch (AI design agent) and Antigravity (agentic IDE). Stitch generates UI designs from text prompts, which are then exported via MCP connectors to Antigravity, where an AI agent writes the full Flutter/Dart codebase following Clean Architecture with Riverpod. The demo builds a Daily Habit Tracker app from prompt to running emulator in about 10-12 minutes. Includes setup steps, example prompts, best practices, and limitations of the agentic approach.

  12. 12
    Article
    Avatar of svelteSvelte Blog·2w

    What’s new in Svelte: April 2026

    April 2026 brings several improvements to Svelte and SvelteKit. Highlights include Svelte MCP integration with OpenCode via the sv CLI, support for functions in svelte.config.js for css/runes/customElement options, new exported types from svelte/motion (TweenOptions, SpringOptions, etc.), server-side error boundary support in SvelteKit, and improved type narrowing for page/layout params with matchers. The community showcase features a range of apps, learning resources, and new libraries built with Svelte.

  13. 13
    Article
    Avatar of phProduct Hunt·5w

    Refero: Design research for humans and AI

    Refero MCP is a tool that gives AI agents access to 125,000+ real product screens and 8,000+ user flows, enabling them to reference actual design patterns instead of generating generic UI. The goal is to improve AI-generated interface quality by grounding it in real-world product design references.

  14. 14
    Article
    Avatar of faunFaun·4w

    System Design — Designing Intelligent UIs as MCP Client

    MCP (Model Context Protocol) enables a new architectural pattern where the UI acts as an intelligent orchestration layer rather than a thin presentation layer. An MCP Client UI can discover backend capabilities at runtime, understand tool schemas, invoke tools dynamically based on LLM reasoning, and chain multi-step workflows without hardcoded API calls. The recommended architecture includes an MCP Client SDK, a Gateway MCP federation layer, and domain-specific MCP Servers. Key scaling considerations cover tool metadata management, multi-tenant isolation, horizontal gateway scaling, and latency optimization through caching and parallel tool execution. Real-world examples include AI-powered IDEs like Cline and Kiro, and Figma's MCP server integration with agents like Cursor and Windsurf.

  15. 15
    Article
    Avatar of swirlaiSwirlAI·3w

    State of Context Engineering in 2026

    Context engineering has matured into a core AI engineering discipline. Five key patterns now define how production agents manage their context windows: (1) Progressive Disclosure via Agent Skills loads instructions in tiers based on relevance rather than upfront; (2) Context Compression uses sliding window plus LLM summarization to shrink accumulated history; (3) Context Routing classifies queries to direct them to the right knowledge source before anything enters the context window; (4) Retrieval Evolution moves from fixed RAG pipelines to agent-controlled loops with Agentic RAG, Graph RAG, and Self-RAG; (5) Tool and Capability Management addresses the hidden token cost of MCP tool schemas (90 tools can consume 50K+ tokens). Each pattern addresses a different failure mode, and production systems layer all five together. Practical starting points are given for each scenario.

  16. 16
    Article
    Avatar of laravelLaravel·4w

    Which AI Model Is Best for Laravel?

    Laravel's team ran a benchmark called Boost Benchmarks, testing six AI models (Claude haiku 4.5, sonnet 4.6, opus 4.6, Kimi k2.5, GPT-5.3 Codex, GPT-5.4) against 17 real Laravel tasks with and without Laravel Boost (an MCP server providing AI coding context). Results show GPT-5.3 Codex and GPT-5.4 tied at 16/17 evaluations passed with Boost enabled, while Kimi k2.5 offered the best speed-accuracy balance at 108s average and 94.6% accuracy. Laravel Boost improved every model tested, with the biggest gains on complex tasks like Livewire, Folio routing, and Inertia shared data. Key findings include LLM non-determinism, configuration errors as a common failure mode, and a small but acceptable token cost overhead from Boost ($0.05–$0.20 per evaluation).

  17. 17
    Article
    Avatar of freecodecampfreeCodeCamp·3w

    The Claude Code Handbook: A Professional Introduction to Building with AI-Assisted Development

    A comprehensive handbook covering Claude Code, Anthropic's AI-powered software development agent. It walks through installation, VS Code setup, subscription tiers, prompt discipline, Plan Mode, feature-by-feature development, token economics, and the internal agent loop mechanics. The guide targets both experienced developers looking to multiply their output and non-technical builders wanting to create software without prior coding experience. Key practices covered include using Plan Mode for 80% of sessions, writing Product Requirements Documents, building incrementally, managing context windows, and understanding how Claude reads codebases selectively via tool calls.

  18. 18
    Article
    Avatar of vigetViget·4w

    Using Claude Code More Intentionally

    A practical guide to setting up Claude Code as a proper development collaborator rather than an ad-hoc chat tool. Key strategies include writing a thorough CLAUDE.md as an onboarding document, using .claudeignore to keep context clean, externalizing plans and artifacts to disk for persistence across sessions, building reusable 'skills' (markdown-defined repeatable processes stored in .claude/skills/), integrating CLI tools and MCP servers for structured external access, and using hooks to automatically run tests or commits after Claude finishes tasks. Also covers remote control via the Claude app for supervising long-running jobs and model switching (Haiku/Sonnet/Opus) to balance cost and capability. The core thesis: invest in the environment and infrastructure around Claude Code, not just the prompts.

  19. 19
    Article
    Avatar of avalonia-blogAvalonia UI Blog·4w

    Accelerate Showcase: Built with AI, Designed with Stitch

    A product manager at Avalonia UI built a polished desktop showcase app without writing any code manually, using Claude Code, Google Stitch for UI design, and Avalonia's DevTools and Parcel MCP servers. The workflow involved generating component skills from documentation, prompting Claude to design and implement an MVVM app targeting .NET 10 for Windows/macOS/Linux, and using the Parcel MCP server to handle cross-platform packaging including macOS code signing and notarization. The result was a shippable app produced in roughly an hour, compared to an estimated week of designer-plus-engineer effort. The post highlights where AI is genuinely useful for Avalonia: building applications with it rather than building the framework itself.

See all mcp archives