Playwright Report MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 625 installs a week from npm. Last commit 28 Oct 2026.
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
We read the source, 4 d ago · rules 995398eba69f
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.
child = spawn(cmd[0], cmd.slice(1), {
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 playwright-report-mcp -- npx -y playwright-report-mcp
{
"mcpServers": {
"playwright-report-mcp": {
"command": "npx",
"args": [
"-y",
"playwright-report-mcp"
]
}
}
}
[mcp_servers.playwright-report-mcp]
command = "npx"
args = ["-y", "playwright-report-mcp"]
{
"mcpServers": {
"playwright-report-mcp": {
"command": "npx",
"args": [
"-y",
"playwright-report-mcp"
]
}
}
}
{
"servers": {
"playwright-report-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"playwright-report-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PW_ALLOWED_DIRS (path.delimiter-separated list of directories the per-call workingDirectory parameter may point at. Entries may be absolute or relative (resolved once against the server's launch cwd at startup). Defaults to '.' (authorizes only the launch directory)), PW_RESULTS_FILE (Absolute path override for the JSON reporter output file. Defaults to <workingDirectory>/test-results/results.json, computed per call).
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
Captured web interfaces, screenshots, flows and structured evidence for AI coding agents.
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.
MCP server for unpacking and analyzing Playwright trace.zip archives
Answers built from our own checks of this server.