Luca

@storybookjs MCP as a bridge between design systems and agents is underrated. Structured component context is exactly what LLMs need to stop hallucinating UI. Nice move.

Storybook MCP for React is here 🎉 Storybook MCP gives AI agents structured context from your components and design system to build better UI the first time. 🧵 ⤵

@Teknium 300 PRs shipped is no joke. Curious how you're handling tool-call reliability at scale, that's been the hardest part to get right in my own agent work. Congrats on the release.

Hermes Agent v0.4.0 — 300 merged PRs this week. Biggest release we've done. Background self-improvement, OpenAI Responses API endpoint for your agent, new messaging platforms, new providers, MCP server management, and a lot more.

@trq212 This is the kind of integration that makes MCP click for people. Built tidal-cli with an MCP server on top. same idea, structured context turns a CLI into something an agent can actually reason with. Great demo.

Today’s Figma MCP update makes it one of the strongest integrations with Claude Code I’ve seen. You can now use Claude Code to design in Figma with the the full context of your design systems.

@tom_doerr AppleScript via MCP is genuinely underrated, suddenly your agent can control any macOS app without a dedicated integration. I built something similar for music playback and the pattern just works. Local-first tooling composing with AI feels like the right stack.

macOS Automator MCP server for AppleScript and JXA github.com/steipete/macos…

@AlgoFoundation @GoPlausible Love seeing niche MCP servers like this, a wallet primitive accessible via standard protocol is exactly the composability that makes the ecosystem interesting. Same reason I built the Tidal MCP server: one tool, any agent can use it.

Your AI agent can now have an Algorand wallet. @GoPlausible just shipped an MCP server giving any AI agent, (such as Claude, Copilot, or Cline) a full Algorand wallet and explorer.​​​​​​​​​​​​​​​​ No app. No browser. Your agent just... has a wallet. Learn more below 👇

@mayukh_panja There's a huge gap between 'tried Copilot once in 2024' and actually running Claude Code as your dev loop. The people still on the fence are sitting on a lot of alpha. Ship something with it and you'll never go back.

I met my academic friends after a long time. All computational physicists. Heavy use of C++ and python. None of them on X. They have NOT heard of Opus 4.6!!!???! Never touched Claude Code. All of them had tried AI coding agents around early 2025, didn’t really find them useful and simply moved on. I tried to push them to use Claude Code, they seemed skeptical, “Does it really work?” Didn’t seem enthusiastic at all. They still see AI as a mostly a gimmick and never really tried anything beyond ChatGPT. I think just being on X right now has insane alpha. It is a completely different world out there.

@Suryanshti777 This is the architecture I've been waiting for. Auto-discovering peers via MCP is clean, way better than duct-taping agents together with a framework. Built something similar for a CLI tool and the coordination overhead just disappears.

Holy shit… someone just made Claude instances talk to each other. Not APIs. Not agents. Not orchestrators. Just multiple Claude Code sessions… messaging each other like coworkers. It’s called claude-peers — and it turns one Claude into a team. Here’s what’s happening: Run 5 Claude Code sessions across different projects Each one auto-discovers the others They send messages instantly Ask questions Share context Coordinate work Your AI tools literally collaborate. Example: Claude A (poker-engine): "what files are you editing?" Claude B (frontend): "working on auth.ts + UI state" Claude A: "ok I'll avoid touching auth logic" No conflicts. No manual coordination. Just AI syncing itself. Under the hood: • Local broker daemon (localhost) • SQLite peer registry • MCP servers per session • Instant channel push messaging • Auto peer discovery • Cross-project communication Everything runs locally. No cloud. No latency. What it unlocks: • Multi-agent coding without frameworks • One Claude writes backend, another frontend • One debugs while another refactors • Research Claude feeds builder Claude • Large projects split across AI workers This is basically: "spawn 5 Claudes and let them coordinate themselves" Even crazier: Each instance auto-summarizes what it's doing Other Claudes can see: • working directory • git repo • current task • active files They know what the others are working on. Commands: • list_peers → find all Claude sessions • send_message → talk to another Claude • set_summary → describe your task • check_messages → manual fallback So you can literally say: "message peer 3: what are you working on?" …and it responds instantly. No orchestration layer. No agent framework. Just Claudes… talking. This is the cleanest multi-agent system I've seen. We're moving from: 1 AI assistant → to AI teams that coordinate themselves. And it's all running on your machine. Wild.

@KanikaBK Obsidian + Claude Code is an insane combo for knowledge work. I use a similar setup for knowledge management. the low cost / high leverage ratio is real, especially once you wire in an MCP server.

🤯 YOUR OBSIDIAN VAULT is worth $120K/YR & you're getting $0 from it. GREG ISENBERG just dropped a 1hr MASTERCLASS on turning Obsidian + Claude Code into a 24/7 personal Operating System. Total Cost: $120/yr This setup: FREE Bookmark before it's buried!

@akshay_pachaar This is exactly how I ended up structuring my tidal-cli MCP server. Once you treat the .claude/ folder as real infrastructure, everything clicks. The skills/agents separation is underrated.

How to setup your Claude code project? TL;DR Most developers skip the setup and just start prompting. That's the mistake. A proper Claude Code project lives inside a .𝗰𝗹𝗮𝘂𝗱𝗲/ folder. Start with 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 as Claude's instruction manual. Split it into a 𝗿𝘂𝗹𝗲𝘀/ folder as it grows. Add 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/ for repeatable workflows, 𝘀𝗸𝗶𝗹𝗹𝘀/ for context-triggered automation, and 𝗮𝗴𝗲𝗻𝘁𝘀/ for isolated subagents. Lock down permissions in 𝘀𝗲𝘁𝘁𝗶𝗻𝗴𝘀.𝗷𝘀𝗼𝗻. There are two .𝗰𝗹𝗮𝘂𝗱𝗲/ folders: one committed with your repo, one global at ~/.𝗰𝗹𝗮𝘂𝗱𝗲/ for personal preferences and auto-memory across projects. The .𝗰𝗹𝗮𝘂𝗱𝗲/ folder is infrastructure. Treat it like one. The article below is a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, custom commands, skills, agents, and permissions, and how to set them up properly.

@mamagnus00 Browser + agent integration is where things get really interesting. Combine this with domain-specific MCP tools (music, data, code) and agents can handle end-to-end workflows.

Easiest way to enable Claude Code and OpenClaw control your browser. - For local: It can use your real browser - For scale: It can use our cloud infra to be undetected

@CoinMarketCap Every API becoming an MCP server is the trend I didn't expect to move this fast. Shipped one for Tidal music last week, same pattern: wrap the API, expose tools, let the agent chain them autonomously.

💡 CoinMarketCap | MCP for AI Agents 💡 Building crypto AI Agents? Stop writing custom integration code. Our MCP server feeds your agents real-time market context. It completely handles endpoint mapping and response formatting for you! Here is how to build smarter 🧵👇 1/5

@_catwu Short sprints + demos over docs is exactly the mindset that works for shipping side projects too. Built tidal-cli in a weekend with the same approach: hip, test with real users, iterate. The todo list tool is underrated.

1/ Plan in short sprints Long roadmaps can't compete with a high velocity of small experiments. Claude Code on Claude desktop, AskUserQuestion tool, and todo lists all started as ideas from the team. We built a prototype, internal users liked it, we shipped it.

The PM playbook was built on an assumption that the technology underneath your product is roughly stable With the current pace of model progress, this is no longer true. Here's how we've evolved the PM role:

@linuxfoundation 180+ tools and 15+ servers at Duolingo — that's the scale we're heading toward. Curious how they handle tool selection at that volume.

180+ MCP tools. 15+ servers. One AI Slackbot. Hear how Aaron Wang (Duolingo) built an enterprise #AI assistant at #MCPDevSummit, April 2–3 in NYC. Register by March 23 to save $400+ ➡️ events.linuxfoundation.org/mcp-dev-summit…

@grinich Server-side token handling is the hardest part. Built a double OAuth flow for my Tidal MCP server (Claude authenticates to my server, my server authenticates to Tidal). Scoped, time-bound credentials is the right approach.

WorkOS Launch Week - Day 4 🔌 Pipes MCP 🔌 Give your agents secure, time-bound access to third-party tools. 🔐Scope access by session to prevent persistent access 🛡️ Audit every call and keep tokens server-side 📡 Connect to Google, Slack, GitHub, Snowflake, and more Read the blog: workos.com/blog/pipes-mcp

@unusual_whales Trading, music, code — every domain is getting its MCP server now. Shipped one for Tidal last week. The pattern is the same everywhere: take a complex API, wrap it in tools, let the agent chain them. Powerful.

BREAKING: We just gave Claude full access to the options, equities, and prediction markets. The Unusual Whales MCP Server plugs into any AI and streams live, structured market data on demand. Build trading bots, smart money dashboards, screeners. Whatever you want. Pull options flow, dark pools, congressional trades, full financials, technicals, 13Fs, insider activity, and Polymarket data with proprietary analytics to instantly spot smart vs retail divergence. It is the most have tool for all vibecoders and traders. Get your API key and start shipping: unusualwhales.com/public-api/mcp

@OdinLovis Connecting 1000+ models through MCP is a great move. I just shipped my own MCP server for Tidal music — 32 tools, same pattern. The protocol is becoming the universal adapter layer for AI agents.

I have been working hard on this one. We just shipped the fal MCP Server, any AI assistant can now search, run, and chain 1,000+ generative AI models from a single conversation. Images, video, audio, 3D one command to connect. Blog → blog.fal.ai/connect-your-a… Docs → docs.fal.ai/documentation/…

Control your @TIDAL account from any MCP client. Search, playlists, playback, artist discovery — 32 tools. No CLI needed. Just connect and ask. Just shipped tidal-cli on @SmitheryAI. #MCP

@ApplyWiseAi @TIDAL DASH downloads + plays locally via ffplay. For agents: every command has --json output, so the agent chains search → create playlist → add tracks autonomously. The OpenClaw skill wraps it into natural language.

@lucaperret @TIDAL dash streaming in cli? how's it hook into agent workflows?

Just shipped tidal-cli — because every music integration out there is built for Spotify. 30+ commands. 111 tests. DASH streaming. Open source. Built for AI agents. @TIDAL #buildinpublic #opensource

@abhinavramesh @TIDAL One weekend. Claude did the heavy lifting I focused on the API design and what I actually wanted as a user. The tests came almost for free with Vitest + Claude generating them from the command specs.

@lucaperret @TIDAL Open source + built for agents is such a good combo. 111 tests on a CLI is solid — how long did this take to ship?

@AnthropicAI Site: tidal-cli.lucaperret.ch GitHub: github.com/lucaperret/tid… OpenClaw skill: clawhub.ai/lucaperret/tid…

Open source. MIT license. TypeScript. Built with @AnthropicAI Claude. npm install -g @lucaperret/tidal-cli What Tidal feature would you automate first? #ClaudeCode #AIagents