five46 runs on your own machine — the client starts it, so there is no endpoint to ping. 57 installs a week from npm. Last commit 28 Aug 2026.
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
We read the source, 8 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.
console.log('Stored as plain JSON with user-only file permissions — not encrypted at rest (the same tradeoff ~/.aws/credentials makes).')
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 five46 -- npx -y five46
{
"mcpServers": {
"five46": {
"args": [
"-y",
"five46"
],
"command": "npx"
}
}
}
[mcp_servers.five46]
command = "npx"
args = ["-y", "five46"]
{
"mcpServers": {
"five46": {
"args": [
"-y",
"five46"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"five46": {
"args": [
"-y",
"five46"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
FIVE46_LLM_PROVIDER (LLM provider to use: openai, anthropic, gemini, groq, or bedrock), FIVE46_LLM_API_KEY (Your own API key for the chosen provider (for bedrock, your AWS region instead)), FIVE46_MCP_ALLOW_WRITES (Set to 1 to unlock POST/PUT/PATCH for the five46_api tool (read-only by default)), FIVE46_MCP_ALLOW_DELETES (Set to 1 to unlock DELETE (five46_api) and destructive-looking browser clicks (five46_test)), FIVE46_MCP_CONCURRENCY (Max concurrent scenarios for story mode (default: 2 for five46_test, 3 for five46_api; hard-capped at 5)).
The author declared them in the registry entry; get the values from the project itself.
Local QA MCP: scan URLs, inspect pages, generate Playwright repros, and run tests.
MCP server that gives AI agents geometric spatial awareness of web page layouts using Playwright
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
Approved test intent, reviewed Playwright automation and run evidence, inside your editor.
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
Local Playwright browser through residential proxies — agent picks country + sticky identity
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
Answers built from our own checks of this server.