Skyvern is answering right now. Last checked moments ago. Last commit 18 Sep 2026.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
{ isContainerized = existsSync("/.dockerenv") } = {},
file_path = os.path.join(self.artifact_folder, f"{int(datetime.now().timestamp())}-{file_name}")
subprocess.run(
f"xwd -root | xwdtopnm 2>/dev/null | pnmtopng > {png_file_path}", shell=True, env={"DISPLAY": ":99"}
app_module = __import__(module)
ENV VITE_SKYVERN_API_KEY=__SKYVERN_API_KEY_PLACEHOLDER__
if forwarded_proto == "https" or external_host.endswith((".ngrok-free.dev", ".ngrok.io")):
app.innerHTML = tfaShell("Authenticate using your passkey.", `
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add skyvern --transport http https://api.skyvern.com/mcp/
{
"mcpServers": {
"skyvern": {
"url": "https://api.skyvern.com/mcp/"
}
}
}
[mcp_servers.skyvern]
url = "https://api.skyvern.com/mcp/"
{
"mcpServers": {
"skyvern": {
"url": "https://api.skyvern.com/mcp/"
}
}
}
{
"mcpServers": {
"skyvern": {
"url": "https://api.skyvern.com/mcp/"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.skyvern.com/mcp/ | streamable-http | sign-in | 391 ms | 0 min ago |
AI browser automation. Write async Python to navigate, click, type, and extract data.
AI browser automation - navigate, click, type, extract content, and run autonomous web tasks
Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs
AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.
Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Local browser automation for MCP clients powered by DrissionPage.
Answers built from our own checks of this server.