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:
- Local Skyvern Server
- Use your favourite LLM to power Skyvern
- 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 ⚠️
-
Install Skyvern
pip install skyvern -
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 -
(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
https://github.com/user-attachments/assets/0c10dd96-c6ff-4b99-ad99-f34a5afd04fe
1
Cursor looking up the top programming jobs in your area
https://github.com/user-attachments/assets/084c89c9-6229-4bac-adc9-6ad69b41327d
Ask Windsurf to do a form 5500 search and download some files
https://github.com/user-attachments/assets/70cfe310-24dc-431a-adde-e72691f198a7
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"
]
}
}
}
Recommend MCP Servers 💡
@browserbasehq/mcp
Allow LLMs to control a browser with Browserbase and Stagehand
Tabby MCP
A Tabby plugin that implements a Model Context Protocol (MCP) server, enabling AI-powered control and automation of the Tabby terminal.
facebook-mcp-server
Facebook MCP server for automating posts, comment moderation, insights, and sentiment filtering.
@debugg-ai/debugg-ai-mcp
An AI-driven browser automation and end-to-end test server implementing the Model Context Protocol (MCP), designed to help AI agents test UI changes, simulate user behavior, and analyze visual outputs of running web applications via natural language and CLI tools.
mcp-filesystem-extended
A Node.js MCP server for comprehensive filesystem operations, including reading, writing, patching, searching, and managing files and directories.