About Playwright E2E MCP
playwright-e2e-mcp is an open-source MCP server for diagnosing and fixing failing Playwright tests. The repository has moved to xsignon-secure/E2E; the npm package name remains unchanged.
Key features
- 01Diagnose failing Playwright tests
- 02Analyze traces
- 03Verify locator fixes
- 04Rank flaky tests
- 05MIT-licensed open source
Use cases
- 01Investigate a failing Playwright test
- 02Review trace data during debugging
- 03Prioritize flaky tests for investigation
MCP support
It is an MCP server for Playwright test diagnosis and repair. The repository and MCP Registry entry have moved to xsignon-secure/E2E.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://playwright-e2e-mcp.vercel.app/api/mcpclaude mcp add --transport http trajectiq-ai-e2e https://playwright-e2e-mcp.vercel.app/api/mcp{"mcpServers":{"trajectiq-ai-e2e":{"type":"http","url":"https://playwright-e2e-mcp.vercel.app/api/mcp"}}}Open in Cursor{"servers":{"trajectiq-ai-e2e":{"type":"http","url":"https://playwright-e2e-mcp.vercel.app/api/mcp"}}}Open in VS Code{"mcpServers":{"trajectiq-ai-e2e":{"type":"http","url":"https://playwright-e2e-mcp.vercel.app/api/mcp"}}}{"mcpServers":{"trajectiq-ai-e2e":{"serverUrl":"https://playwright-e2e-mcp.vercel.app/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
11| Parameter | Type | Required | Description |
|---|---|---|---|
| args | array | No | Extra Playwright flags from an allowlist, as --flag or --flag=value (e.g. --repeat-each=3, --shard=1/2, --trace=on) |
| grep | string | No | Only run tests whose title matches this regex |
| config | string | No | playwright.config path or 1-based index when the project has several configs |
| headed | boolean | No | Run with a visible browser window |
| browser | enum | No | Playwright project name to run (matched against playwright.config projects)chromium | firefox | webkit |
| retries | integer | No | |
| workers | integer | No | |
| testFiles | array | No | Test files/directories relative to the project root; "file:line" is supported. Omit to run the whole suite. |
| timeoutMs | integer | No | Hard wall-clock limit for the whole run; the process tree is killed past it (default 120000) |
| background | boolean | No | Return a run id at once; poll get-run-status |
| lastFailed | boolean | No | Only re-run tests that failed in the previous run (Playwright --last-failed) — the fast fix → re-run loop |
| projectRoot | string | No | Project directory; defaults to the server working directory |
| testTimeoutMs | integer | No | Per-test timeout passed to Playwright |
| retryOnFailure | boolean | No | Auto retry failing tests once before reporting failure (default true; ignored when retries is set) |
Details
From the project READMEplaywright-e2e-mcp has moved
This repository is no longer maintained. playwright-e2e-mcp now lives at github.com/xsignon-secure/E2E.
The latest release is 0.4.2. To set it up in your project:
npx -y playwright-e2e-mcp init
The npm package name is unchanged, so existing installs keep working; run the command above
(or npm install -D playwright-e2e-mcp@latest) to pick up the newest version.
Issues, pull requests, releases and the .mcpb Claude Desktop bundle are all at the new home:
- Repository: https://github.com/xsignon-secure/E2E
- Releases: https://github.com/xsignon-secure/E2E/releases
- MCP Registry name:
io.github.xsignon-secure/E2E
playwright-e2e-mcp is, and stays, fully open source and free under the MIT license.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.