Puppetflow is listed as active in the registry but did not answer our last check.
Build, run, monitor, and control Puppetflow browser automations from AI clients.
The linked repository no longer exists on GitHub — it was deleted or made private.
We read the source, 1 d 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.
if (file_exists('/.dockerenv')) {
require $maintenance;
process.env.SANDBOX_NODE_MODULES_PATH ? path.join(process.env.SANDBOX_NODE_MODULES_PATH, moduleName) : null,
bridgeFunctions[bridgeFunctionNames[ef]] = new Function('return ' + hydratableBridgeFunctions[bridgeFunctionNames[ef]])();
$process = proc_open(
private const API_BASE = 'https://api.telegram.org/bot';
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 12 min ago.
claude mcp add mcp --transport http https://{instance_host}/api/workspaces/{workspace}/mcp-server/http
{
"mcpServers": {
"mcp": {
"url": "https://{instance_host}/api/workspaces/{workspace}/mcp-server/http"
}
}
}
[mcp_servers.mcp]
url = "https://{instance_host}/api/workspaces/{workspace}/mcp-server/http"
{
"mcpServers": {
"mcp": {
"url": "https://{instance_host}/api/workspaces/{workspace}/mcp-server/http"
}
}
}
{
"mcpServers": {
"mcp": {
"url": "https://{instance_host}/api/workspaces/{workspace}/mcp-server/http"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://{instance_host}/api/workspaces/{workspace}/mcp-server/http | streamable-http | answering | 1 ms | 12 min ago |
Build, run, inspect, and publish browser extensions from any MCP client. 30 tools, 11 browsers.
Create and control browser sessions for web automation, testing, and AI agent tasks
AI browser automation - navigate, click, type, extract content, and run autonomous web tasks
Local browser automation for MCP clients powered by DrissionPage.
Web data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation
Browser automation for MCP clients via Zen Browser. Parallel multi-tab, content extraction.
MCP server for Safari DevTools — browser debugging and automation for AI coding agents
Selenium MCP server for AI agents — 41 browser automation tools with snapshots and sessions.
Answers built from our own checks of this server.