The aiup-playwright skill works without any MCP server — it falls back to your own knowledge and the documentation links inside the skill. The servers below look up current @playwright/test documentation and let the agent open the running application in a browser, take an accessibility snapshot, and try a locator before it writes it into a test. They are advisory only; nothing in the skill hard-requires them.

Servers

Server	Type	URL / command	Used by
context7	http	`https://mcp.context7.com/mcp`	`playwright-e2e-test` (`@playwright/test` documentation)
playwright	stdio	`npx @playwright/mcp@latest`	`playwright-e2e-test` (exploring the UI, debugging tests)

Configure in Claude Code

Add them to your project's .mcp.json (the Tessl tessl mcp start bridge can stay alongside them):

{
  "mcpServers": {
    "context7": {
      "type": "http",
      "url": "https://mcp.context7.com/mcp"
    },
    "playwright": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@playwright/mcp@latest"
      ]
    }
  }
}

For other agents (Cursor, Gemini, Codex, Copilot), add the same servers to that agent's MCP configuration file.

Note for Tessl-installed users

Tessl ships them with the plugin: tessl install reads the plugin's bundled .mcp.json and writes them into the MCP configuration of each agent it configures, as the Claude Code marketplace install does. If your agent does not list them after the install — an agent Tessl does not configure, or a manual skill copy — configure the servers above manually as shown.