Cowork QA runs on your own machine — the client starts it, so there is no endpoint to ping. 28 installs a week from npm. Last commit 6 May 2026.
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
We read the source, 19 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.
postinstall: playwright install chromium
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 cowork-qa -- npx -y cowork-qa-mcp
{
"mcpServers": {
"cowork-qa": {
"args": [
"-y",
"cowork-qa-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.cowork-qa]
command = "npx"
args = ["-y", "cowork-qa-mcp"]
{
"mcpServers": {
"cowork-qa": {
"args": [
"-y",
"cowork-qa-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"cowork-qa": {
"args": [
"-y",
"cowork-qa-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
COWORK_QA_HEADED (Set to '1' to launch Chromium with a visible window instead of headless.), COWORK_QA_DATA (Directory where session traces (<session-id>.json) are written. Defaults to <cwd>/.cowork-qa.).
The author declared them in the registry entry; get the values from the project itself.
Selenium MCP server for AI agents — 41 browser automation tools with snapshots and sessions.
Browser MCP: drive a real Chromium via Playwright with compact ref-addressable page snapshots
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
Drive a real Playwright browser: annotated screenshot + structured page state after every action.
Token-optimized interaction graph for AI browser agents — 71% fewer tokens than ARIA snapshots.
Browser automation for AI agents: compressed page snapshots, batched actions, fewer tokens.
MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
MCP server providing Playwright test generation wizard with intelligent prompts and best practices
Answers built from our own checks of this server.