Skyvern MCP & Skills - Let Claude code and Open Claw automate the web

🚀🚀🚀 We're excited to launch Skyvern MCP — give your AI assistant superpowers to browse the web, fill out forms, extract data, and run multi-step automations. Works with OpenClaw, Claude Code, Codex, Cursor, or your custom agent.

🎯 Get started at app.skyvern.com or check out the open source repo at github.com/Skyvern-AI/skyvern.

Skyvern MCP connects your favorite AI assistant to a real cloud browser through the Model Context Protocol. Instead of writing Selenium scripts or wrestling with CSS selectors, you just tell your AI what to do in plain English — and Skyvern handles the rest.

⚡ Setup takes 30 seconds. Seriously.

No Python. No pip install. No local server. One line of config, and your AI assistant can browse the web:

claude mcp add-json skyvern '{"type":"http","url":"https://api.skyvern.com/mcp/","headers":{"x-api-key":"YOUR_API_KEY"}}'

That's it. Your AI now has access to 33 browser automation tools across 6 categories.

❓ How is this different from other browser automation tools?

Traditional browser automation (Selenium, Playwright, Puppeteer) requires you to write code, manage selectors, and handle every edge case manually. Skyvern MCP flips this on its head:

🗣️ Natural language, not code — Say "Submit this" instead of writing document.querySelector('#btn-submit-form-v2').click()

🧠 AI-powered extraction — Ask "extract all job listings with title, company, and salary" and get back clean JSON

✅ AI validation — Check conditions like "is the user logged in?" and get a true/false answer

🔄 Reusable workflows — Chain actions into multi-step automations you can run again and again

☁️ Cloud browsers — No local browser needed. Skyvern runs browsers in the cloud with geographic proxy support

🤔 What can you actually do with it?

Here are real use cases we see every day:

📊 "Go to Hacker News and get the top 10 posts with titles and scores" — Your AI opens a browser, navigates, extracts structured data, and returns it to you

📝 "Fill out this government form with my business details" — Multi-page form automation with intelligent field detection

🧾 "Log into my vendor portal and download last month's invoices" — Secure credential-based login + file download

🔍 "Search the Secretary of State website and verify this business registration" — Multi-step research across dynamic pages

💼 "Find remote Python jobs on Indeed paying over $150k" — Navigate, filter, extract, all in one conversation

🛠️ 33 Tools. 6 Categories. Infinite Possibilities.

🤩 We're open source!

Skyvern is fully open source with over ⭐️ 20K+ Stars on GitHub ⭐️. Check out the repo: github.com/Skyvern-AI/skyvern

Want to self-host? Just pip install skyvern

Want the MCP? Follow the instructions here

Want the skills? Follow the instructions here

🖥️ Works with all the tools you already use

• OpenClaw

• Claude Desktop

• Claude Code

• Cursor

• Codex

• Any MCP-compatible client

📞 Want to build complex automations?

We'd love to help! Shoot me an email at founders@skyvern.com and let's chat about what you're building.

🎁 Launch Offer

We're giving everyone a 10% discount to try Skyvern MCP. Get started here: app.skyvern.com and use the coupon code PH10 Happy automating! We'd love to see the creative ways you put your coding agent to work in the browser.

Let's go, @suchintan_singh!! I was excited to see that you and Shuchang are also launching today

Congrats on your 4th launch! One thing I've been wrestling with on the MCP side: The protocol is stateless but browser sessions obviously aren't. When someone's agent logs into a portal, clicks through three pages, and pulls invoices, how are you keeping that session alive between tool calls? Are you pinning to a browser instance on your end?

That stateless-protocol-meets-stateful-browser tension is one of the more interesting design problems in the MCP ecosystem right now.

Great product and a great team that really cares about seeing their customers succeed!

Does this solve captchas as well? I know I'm not the only one who hates those. Any new user discounts?

The combination of MCP integration with pre-built Skills is really compelling for teams already using Claude - it essentially turns browser automation from a dev task into something anyone can trigger conversationally. What kind of error recovery does Skyvern handle when a website layout changes unexpectedly mid-workflow?

Sub-agents that learn and maintain automations on their own is a nice abstraction. How do they handle sites that change their DOM frequently — does it self-heal or does it flag for human review?

Skyvern can do so many incredible things - and being able to integrate it into llm workflows is such a choice upgrade. Nice work on this! Congrats to you and the team @suchintan_singh🙌

Just tried it out for our current setup with Skyvern - it's solid!

Big kudos, this is a genuinely great product you’ve built!