Skyvern Advanced Browser Automation

Created By
Skyvern-AIa year ago
Overview

What is Skyvern?

Skyvern is an advanced browser automation tool that utilizes Large Language Models (LLMs) and computer vision to automate browser-based workflows, providing a more reliable solution compared to traditional automation methods.

How to use Skyvern?

To use Skyvern, you can either run it locally by installing it via pip or use the managed Skyvern Cloud service. For local use, install with pip install skyvern, then run tasks using the provided API. For cloud use, create an account at app.skyvern.com.

Key features of Skyvern?

  • Automates complex browser workflows using LLMs and computer vision.
  • Supports both local and cloud-based execution.
  • Capable of handling dynamic web content without relying on brittle XPath selectors.
  • Offers features like task chaining, data extraction, and form filling.

Use cases of Skyvern?

  1. Automating job applications across multiple platforms.
  2. Downloading invoices from various websites.
  3. Filling out government forms and applications.
  4. Retrieving insurance quotes from providers in different languages.

FAQ from Skyvern?

  • Can Skyvern automate any website?
    Yes, Skyvern can automate interactions on websites it has never seen before by using visual elements instead of predefined selectors.

  • Is there a cloud version of Skyvern?
    Yes, Skyvern Cloud allows users to run multiple instances without managing infrastructure.

  • What programming language is required?
    Skyvern requires Python 3.11 or higher for local installations.

Server Config

{
  "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"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Skyvern-AI
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago