Skyvern automates browser-based workflows using LLMs and computer vision, providing a Playwright-compatible SDK and a no-code workflow builder for users to automate tasks on any website.
From the registry: AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
$ pip install skyvern && skyvern quickstarthttps://www.skyvern.comPlease install the `skyvern` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.11** — Python 3.11.x or 3.12 required (not 3.13) (https://www.python.org/downloads/)
- **Install Skyvern** — Install the skyvern package and run quickstart Run: `pip install skyvern && skyvern quickstart` (https://www.skyvern.com)
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","skyvern.cli.mcp_tools"]
- optional environment variables:
- `SKYVERN_API_KEY`: API key for Skyvern Cloud. Not needed for local mode. (example: `<your_api_key>`)
Note: Skyvern is primarily a browser automation tool with MCP support. See MCP docs at https://github.com/Skyvern-AI/skyvern/blob/main/skyvern/cli/mcp_tools/README.md. Supports many LLM providers via environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.).
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.API_KEYrequiredUsed to authenticate with Skyvern Cloud.CHROME_EXECUTABLE_PATHrequiredPath to the Chrome browser executable for local browser control.BROWSER_TYPErequiredSpecifies the type of browser connection (e.g., cdp-connect).MCP server for Firecrawl web scraping, structured data extraction and web search integration.