Skyvern MCP server

Skyvern's MCP server implementation creates a bridge between AI applications and web browsers, enabling your AI apps to interact with websites. This allows for capabilities like form completion, file downloads, web research, and various other browser-based tasks without requiring human intervention.

Installation

Skyvern requires Python 3.11 to run properly. To get started:

1. Install the Skyvern package:

pip install skyvern

2. Set up your configuration with the guided wizard:

skyvern init

3. If using local mode (not Skyvern Cloud), launch the Skyvern server:

skyvern run server

Connection Options

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

Local Skyvern Server

Use this option to power Skyvern with your preferred LLM locally. During the skyvern init process, you'll be guided through setting up a local server.

Skyvern Cloud

For cloud-based usage:

1. Create an account at app.skyvern.com
2. Get your API key from the settings page
3. Use this API key during the skyvern init process when prompted

Compatible Applications

Skyvern works with several MCP-enabled applications, including:

• Cursor
• Windsurf
• Claude Desktop
• Custom MCP applications

Manual Configuration

For applications not directly supported by the init wizard, you can use the following configuration template:

{
  "mcpServers": {
    "Skyvern": {
      "env": {
        "SKYVERN_BASE_URL": "https://api.skyvern.com", 
        "SKYVERN_API_KEY": "YOUR_SKYVERN_API_KEY"
      },
      "command": "PATH_TO_PYTHON",
      "args": [
        "-m",
        "skyvern",
        "run",
        "mcp"
      ]
    }
  }
}

Notes:

• For local running, replace https://api.skyvern.com with http://localhost:8000
• Find your local API key in the .env file after running skyvern init, or in your Skyvern Cloud console if using cloud mode
• Replace PATH_TO_PYTHON with the path to your Python 3.11 executable

Use Cases

With Skyvern, AI applications can perform web-based tasks such as:

• Looking up information on websites like Hacker News
• Searching for and analyzing job listings
• Completing and submitting complex forms
• Downloading files from web sources
• Conducting research across multiple web pages

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.