Siteglass runs on your own machine — the client starts it, so there is no endpoint to ping. 63 installs a week from npm. Last commit 20 Jul 2026.
Archive any URL to a shareable rrweb/pdf/png snapshot + agent-driven web QA (scan, run E2E flows).
We read the source, 18 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.
try { await page.screenshot({ path: path.join(shotDir, fn) }); rec.shot = fn; } catch(_){} }
const child = spawn(process.execPath, [path.join(HERE, "crawl.cjs"), url, opts], { env: process.env });
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.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y siteglass-mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"siteglass-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "siteglass-mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"siteglass-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"siteglass-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SITEGLASS_API_KEY (siteglass API key (optional; the server auto-creates an account if absent).), SITEGLASS_BASE_URL (API base URL (default https://siteglass.io).).
The author declared them in the registry entry; get the values from the project itself.
Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.
Gives an AI agent a disposable email and a real UK phone number to test signup flows.
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.
Drive the iOS Simulator from an agent: read the screen, tap/type/swipe, replay flows in CI.
Drive OctoPerf load testing from any AI agent: import, edit, validate, run scenarios, read metrics.
Test iOS, Android, and web apps with agent exploration, replayable flows, and CI gates.
QA + a11y scanner: walks your running app's real user flows and reports what's broken.
MCP server for agent-driven React Native and Expo development and mobile testing
Answers built from our own checks of this server.