Model Context Protocol (MCP)

Skyvern's MCP server implementation helps connect your AI Applications to the browser. This allows your AI applications to do things like: Fill out forms, download files, research information on the web, and more.

You can connect your MCP-enabled applications to Skyvern in two ways:

1. Local Skyvern Server
   • Use your favourite LLM to power Skyvern
2. Skyvern Cloud
   • Create an account at app.skyvern.com
   • Get the API key from the settings page which will be used for setup

Quickstart

⚠️ REQUIREMENT: Skyvern only runs in Python 3.11 environment today ⚠️

1. Install Skyvern
   pip install skyvern
2. Configure Skyvern Run the setup wizard which will guide you through the configuration process. You can connect to either Skyvern Cloud or a local version of Skyvern.
   skyvern init
3. (Optional) Launch the Skyvern Server. Only required in local mode
   skyvern run server

Examples

Skyvern allows Claude to look up the top Hackernews posts today

claude_mcp_demo.mp4

Cursor looking up the top programming jobs in your area

cursor_search_jobs.mp4

Ask Windsurf to do a form 5500 search and download some files

windsurf_demo_fast.mp4

Supported Applications

skyvern init helps configure the following applications for you:

• Cursor
• Windsurf
• Claude Desktop
• Your custom MCP App?

Use the following config if you want to set up Skyvern for any other MCP-enabled application

{ "mcpServers": { "Skyvern": { "env": { "SKYVERN_BASE_URL": "https://api.skyvern.com", # "http://localhost:8000" if running locally "SKYVERN_API_KEY": "YOUR_SKYVERN_API_KEY" # find the local SKYVERN_API_KEY in the .env file after running skyvern init or in your Skyvern Cloud console }, "command": "PATH_TO_PYTHON", "args": [ "-m", "skyvern", "run", "mcp" ] } } }