Time to connect your Grok bot to 9,000+ more apps 🔥
• Tell it "@bot add Zapier plugin"
• Approve the sign-in
• Put it to work in the apps you already use
Zapier MCP is growing 4x faster than Zapier did at a similar scale.
People want to build from anywhere and everywhere.
For most of @Zapier's 15 years, you opened the Zap editor, picked a trigger, and wired up each step yourself.
But now people start wherever they use AI: Claude, ChatGPT, Muse, etc. They describe what they need, and the AI reaches their apps through Zapier MCP.
Every new AI tool becomes a front door to Zapier. In Muse's launch week, more people added Zapier MCP there than to ChatGPT.
All of that growth is still what our team calls "fingertip work." Someone asks their AI to do one thing in their apps, Zapier MCP does it, and then it waits for the next request.
The next frontier is automations that run on their own... That's 𝗡𝗲𝘅𝘁 𝗚𝗲𝗻 𝗭𝗮𝗽𝘀, in early access now.
Describe the job once, wherever you build, and it deploys a Zap that keeps running after you close the chat (or the laptop). It can even fix itself if something goes wrong. We're bringing Zapier to a whole new world of builders.
If you want to last 15 years in tech, you have to reinvent yourself.
To try Next Gen Zaps early, join the waitlist here: https://t.co/LLrVYe0Qwj
I saw the news earlier this week and knew we had to be in it
My team moved fast and Zapier is now a design partner on the open standard for how a person’s agent works with a company
Agents shouldn’t pretend to be you. They should use the connections that already run the work
Zapier is now a connector in Muse!
Just tell your agent to build you a Zap.
For example: “I need a brief before every big call: attendees, account details, recent emails, news, etc. Build it in Zapier”
Muse, Meta's new personal agent, connects to Zapier MCP and builds your workflow as a Next Gen Zap. It’ll pick the apps based on what you use in Zapier, wire up the steps, and deploy it to run autonomously. It can also take one-off actions across 9,000+ apps through Zapier.
Getting started with Muse? Instead of connecting each tool individually, just connect Zapier.
Zapier MCP is available in Muse, Grok Bot, Claude, ChatGPT, and anywhere you build with AI.
Next Gen Zaps in early access now.
Claude for Small Business is here!
Zapier connects it to over 9,000 tools 🧰
Claude for Small Business ships with 27 tools connected. When Claude needs an app beyond that, Zapier MCP connects you instantly.
Plus, it comes with 45 ready-made skills for running and growing a business.
It's already been installed over 775k times!
Learn more here: https://t.co/hn4E905eMA
Your apps are already provisioned. Your AI just can't reach them. Ask it to use Zapier's MCP - https://t.co/14wpaZ70vJ
- Credentials never reach the agent or the developer
- The agent can only do what the user can
- One place to grant, one place to revoke
6/ my read: job two is the bigger opportunity, and its bigger because its empty. job one automates a motion everyone already runs. job two is one most havent noticed started.
5/ everything changes when the buyer is a machine. a16z put it well: the web's model was distraction, and agents dont get distracted. no brand colors. it reads your docs, calls your tool, moves on. no funnel.
4/ job two is my whole job at zapier. the searcher used to be a vibe coder who just wants to connect their apps safely and smash approve. now the searcher is the agent acting for them.
3/ job two: selling TO agents. when an AI agent goes to connect an app or pick a tool, does it pick you? @biilmann named the discipline: agent experience, AX. way less crowded. way more interesting.
7/ this is the cheapest agent-readiness instrument you have. already running, every repo you own, free. pull it weekly, track the clone-to-view gap + top paths. youll see agent interest move before any dashboard does.
1/ agents read your github repo before they recommend your tool. github wont tell you which visitors were agents. but the traffic api gives you enough to infer it, and almost nobody looks 🧵
6/ the honest limit: github doesnt expose user-agent per view. you cant prove claude fetched it. you infer from the four reads. want proof? you need a property you control + its server logs.
5/ read #3: paths. the tell isnt your README. its machine-readable files climbing the list: AGENTS.md, a SKILL.md, the examples dir. when the files written for agents outrank the page written for humans, agents are reading.