[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_115":116},"routes/modules.$creator.$moduleId",{"_14":15,"_16":17,"_18":19,"_20":21},"routes/modules.$creator.$moduleId.endpoints",{"_11":12,"_13":-5},"error","Module not found","tools","module",{"_20":22,"_23":24,"_25":26,"_27":28,"_29":30,"_31":32,"_33":34,"_35":26,"_36":37,"_38":-5,"_39":-5,"_40":-5,"_41":42,"_43":44,"_45":46,"_47":48,"_49":50,"_51":52,"_53":54,"_55":-5,"_56":48,"_57":58,"_59":60,"_61":-5,"_62":-5,"_63":-5,"_64":-5,"_65":66,"_67":68,"_69":70,"_71":72,"_73":74,"_75":-5,"_76":-5,"_77":-5,"_78":48,"_79":-5,"_80":81,"_82":83,"_84":85,"_86":87,"_88":89,"_90":91,"_92":93},"apiUrl","https://odel.app/api","creator","microsoft","moduleId","playwright-mcp","@microsoft/playwright-mcp","displayName","playwright mcp","tagline","Playwright Tools for MCP","iconKey","https://avatars.githubusercontent.com/u/6154722?v=4","category","local","status","published","visibility","public","metaDescription","deploymentType","external","workerName","bindingName","mcpConfig","pricingModel","free","creatorUserId","system:external-import","createdAt",1783342392000,"updatedAt",1788068997000,"sourceRegistry","official-mcp-registry","sourceUrl","https://registry.modelcontextprotocol.io/v0/servers?search=io.github.microsoft%2Fplaywright-mcp","sourceVerified",true,"sourceMissingSince","importedAt","upstreamStars",36611,"upstreamUpdatedAt",1787957081000,"detectedTransport","detectedAuthType","probeStatus","lastProbedAt","githubRepoUrl","https://github.com/microsoft/playwright-mcp","githubRepoFullName","microsoft/playwright-mcp","releaseId","ext-microsoft-playwright-mcp","version","0.0.79","descriptionMarkdown","## Playwright MCP\n\nA Model Context Protocol (MCP) server that provides browser automation capabilities using [Playwright](https://playwright.dev). This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.\n\n### Playwright MCP vs Playwright CLI\n\nThis package provides MCP interface into Playwright. If you are using a **coding agent**, you might benefit from using the [CLI+SKILLS](https://github.com/microsoft/playwright-cli) instead.\n\n- **CLI**: Modern **coding agents** increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows.
**Learn more about [Playwright CLI with SKILLS](https://github.com/microsoft/playwright-cli)**.\n\n- **MCP**: MCP remains relevant for specialized agentic loops that benefit from persistent state, rich introspection, and iterative reasoning over page structure, such as exploratory automation, self-healing tests, or long-running autonomous workflows where maintaining continuous browser context outweighs token cost concerns.\n\n### Key Features\n\n- **Fast and lightweight**. Uses Playwright's accessibility tree, not pixel-based input.\n- **LLM-friendly**. No vision models needed, operates purely on structured data.\n- **Deterministic tool application**. Avoids ambiguity common with screenshot-based approaches.\n\n### Requirements\n- Node.js 18 or newer\n- VS Code, Cursor, Windsurf, Claude Desktop, Goose, Grok, Junie or any other MCP client\n\n\n\n### Getting started\n\nFirst, install the Playwright MCP server with your client.\n\n**Standard config** works in most of the tools:\n\n```js\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n\n[ $\"Install$ ](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522playwright%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540playwright%252Fmcp%2540latest%2522%255D%257D) [ $\"Install$ ](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522playwright%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540playwright%252Fmcp%2540latest%2522%255D%257D)\n\n

Amp

\n\nAdd via the Amp VS Code extension settings screen or by updating your settings.json file:\n\n```json\n\"amp.mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n}\n```\n\n**Amp CLI Setup:**\n\nAdd via the `amp mcp add` command below\n\n```bash\namp mcp add playwright -- npx @playwright/mcp@latest\n```\n\n

\n\n

Antigravity

\n\nAdd via the Antigravity settings or by updating your configuration file:\n\n```json\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n\n

\n\n

Claude Code

\n\nUse the Claude Code CLI to add the Playwright MCP server:\n\n```bash\nclaude mcp add playwright npx @playwright/mcp@latest\n```\n

\n\n

Claude Desktop

\n\nFollow the MCP install [guide](https://modelcontextprotocol.io/quickstart/user), use the standard config above.\n\n

\n\n

Cline

\n\nFollow the instruction in the section [Configuring MCP Servers](https://docs.cline.bot/mcp/configuring-mcp-servers)\n\n**Example: Local Setup**\n\nAdd the following to your [`cline_mcp_settings.json`](https://docs.cline.bot/mcp/configuring-mcp-servers#editing-mcp-settings-files) file:\n\n```json\n{\n \"mcpServers\": {\n \"playwright\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"timeout\": 30,\n \"args\": [\n \"-y\",\n \"@playwright/mcp@latest\"\n ],\n \"disabled\": false\n }\n }\n}\n```\n\n

\n\n

Codex

\n\nUse the Codex CLI to add the Playwright MCP server:\n\n```bash\ncodex mcp add playwright npx \"@playwright/mcp@latest\"\n```\n\nAlternatively, create or edit the configuration file `~/.codex/config.toml` and add:\n\n```toml\n[mcp_servers.playwright]\ncommand = \"npx\"\nargs = [\"@playwright/mcp@latest\"]\n```\n\nFor more information, see the [Codex MCP documentation](https://github.com/openai/codex/blob/main/codex-rs/config.md#mcp_servers).\n\n

\n\n

Copilot

\n\nUse the Copilot CLI to interactively add the Playwright MCP server:\n\n```bash\n/mcp add\n```\n\nAlternatively, create or edit the configuration file `~/.copilot/mcp-config.json` and add:\n\n```json\n{\n \"mcpServers\": {\n \"playwright\": {\n \"type\": \"local\",\n \"command\": \"npx\",\n \"tools\": [\n \"*\"\n ],\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n\nFor more information, see the [Copilot CLI documentation](https://docs.github.com/en/copilot/concepts/agents/about-copilot-cli).\n\n

\n\n

Cursor

\n\n#### Click the button to install:\n\n[ $\"Install$ ](https://cursor.com/en/install-mcp?name=Playwright&config=eyJjb21tYW5kIjoibnB4IEBwbGF5d3JpZ2h0L21jcEBsYXRlc3QifQ%3D%3D)\n\n#### Or install manually:\n\nGo to `Cursor Settings` -> `MCP` -> `Add new MCP Server`. Name to your liking, use `command` type with the command `npx @playwright/mcp@latest`. You can also verify config or add command like arguments via clicking `Edit`.\n\n

\n\n

Factory

\n\nUse the Factory CLI to add the Playwright MCP server:\n\n```bash\ndroid mcp add playwright \"npx @playwright/mcp@latest\"\n```\n\nAlternatively, type `/mcp` within Factory droid to open an interactive UI for managing MCP servers.\n\nFor more information, see the [Factory MCP documentation](https://docs.factory.ai/cli/configuration/mcp).\n\n

\n\n

Gemini CLI

\n\nFollow the MCP install [guide](https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md#configure-the-mcp-server-in-settingsjson), use the standard config above.\n\n

\n\n

Goose

\n\n#### Click the button to install:\n\n[![Install in Goose](https://block.github.io/goose/img/extension-install-dark.svg)](https://block.github.io/goose/extension?cmd=npx&arg=%40playwright%2Fmcp%40latest&id=playwright&name=Playwright&description=Interact%20with%20web%20pages%20through%20structured%20accessibility%20snapshots%20using%20Playwright)\n\n#### Or install manually:\n\nGo to `Advanced settings` -> `Extensions` -> `Add custom extension`. Name to your liking, use type `STDIO`, and set the `command` to `npx @playwright/mcp`. Click \"Add Extension\".\n

\n\n

Grok

\n\nUse the Grok CLI to add the Playwright MCP server:\n\n```bash\ngrok mcp add playwright -- npx @playwright/mcp@latest\n```\n\nAlternatively, create or edit the configuration file `~/.grok/config.toml` and add:\n\n```toml\n[mcp_servers.playwright]\ncommand = \"npx\"\nargs = [\"@playwright/mcp@latest\"]\n```\n\nFor more information, see the [Grok MCP documentation](https://docs.x.ai/build/features/mcp-servers).\n\n

\n\n

Junie

\n\nTo add the Playwright MCP server in Junie CLI:\n\n1. Type `/mcp`\n2. Press `Ctrl+A` to add a new MCP server\n3. Select **Playwright** from the list\n\nAlternatively, add to `.junie/mcp/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"Playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n\nFor more information, see the [Junie MCP configuration documentation](https://junie.jetbrains.com/docs/junie-cli-mcp-configuration.html).\n\n

\n\n

Kiro

\n\n[![Add to Kiro](https://kiro.dev/images/add-to-kiro.svg)](https://kiro.dev/launch/mcp/add?name=playwright&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22%40playwright%2Fmcp%40latest%22%5D%7D)\n\nFollow the MCP Servers [documentation](https://kiro.dev/docs/mcp/). For example in `.kiro/settings/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n

\n\n

LM Studio

\n\n#### Click the button to install:\n\n[![Add MCP Server playwright to LM Studio](https://files.lmstudio.ai/deeplink/mcp-install-light.svg)](https://lmstudio.ai/install-mcp?name=playwright&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyJAcGxheXdyaWdodC9tY3BAbGF0ZXN0Il19)\n\n#### Or install manually:\n\nGo to `Program` in the right sidebar -> `Install` -> `Edit mcp.json`. Use the standard config above.\n

\n\n

opencode

\n\nFollow the MCP Servers [documentation](https://opencode.ai/docs/mcp-servers/). For example in `~/.config/opencode/opencode.json`:\n\n```json\n{\n \"$schema\": \"https://opencode.ai/config.json\",\n \"mcp\": {\n \"playwright\": {\n \"type\": \"local\",\n \"command\": [\n \"npx\",\n \"@playwright/mcp@latest\"\n ],\n \"enabled\": true\n }\n }\n}\n\n```\n

\n\n

Qodo Gen

\n\nOpen [Qodo Gen](https://docs.qodo.ai/qodo-documentation/qodo-gen) chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the standard config above.\n\nClick Save.\n

\n\n

VS Code

\n\n#### Click the button to install:\n\n[ $\"Install$ ](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522playwright%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540playwright%252Fmcp%2540latest%2522%255D%257D) [ $\"Install$ ](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522playwright%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540playwright%252Fmcp%2540latest%2522%255D%257D)\n\n#### Or install manually:\n\nFollow the MCP install [guide](https://code.visualstudio.com/docs/copilot/chat/mcp-servers#_add-an-mcp-server), use the standard config above. You can also install the Playwright MCP server using the VS Code CLI:\n\n```bash\n# For VS Code\ncode --add-mcp '{\"name\":\"playwright\",\"command\":\"npx\",\"args\":[\"@playwright/mcp@latest\"]}'\n```\n\nAfter installation, the Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.\n

\n\n

Warp

\n\nGo to `Settings` -> `AI` -> `Manage MCP Servers` -> `+ Add` to [add an MCP Server](https://docs.warp.dev/knowledge-and-collaboration/mcp#adding-an-mcp-server). Use the standard config above.\n\nAlternatively, use the slash command `/add-mcp` in the Warp prompt and paste the standard config from above:\n```js\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\"\n ]\n }\n }\n}\n```\n\n

\n\n

Windsurf

\n\nFollow Windsurf MCP [documentation](https://docs.windsurf.com/windsurf/cascade/mcp). Use the standard config above.\n\n

\n\n### Configuration\n\nPlaywright MCP server supports following arguments. They can be provided in the JSON configuration above, as a part of the `\"args\"` list:\n\n\n\n| Option | Description |\n|--------|-------------|\n| --allowed-hosts | comma-separated list of hosts this server is allowed to serve from. Defaults to the host the server is bound to. Pass '*' to disable the host check.
*env* `PLAYWRIGHT_MCP_ALLOWED_HOSTS` |\n| --allowed-origins | semicolon-separated list of TRUSTED origins to allow the browser to request. Default is to allow all. Important: *does not* serve as a security boundary and *does not* affect redirects.
*env* `PLAYWRIGHT_MCP_ALLOWED_ORIGINS` |\n| --allow-unrestricted-file-access | allow access to files outside of the workspace roots. Also allows unrestricted access to file:// URLs. By default access to file system is restricted to workspace root directories (or cwd if no roots are configured) only, and navigation to file:// URLs is blocked.
*env* `PLAYWRIGHT_MCP_ALLOW_UNRESTRICTED_FILE_ACCESS` |\n| --blocked-origins | semicolon-separated list of origins to block the browser from requesting. Blocklist is evaluated before allowlist. If used without the allowlist, requests not matching the blocklist are still allowed. Important: *does not* serve as a security boundary and *does not* affect redirects.
*env* `PLAYWRIGHT_MCP_BLOCKED_ORIGINS` |\n| --block-service-workers | block service workers
*env* `PLAYWRIGHT_MCP_BLOCK_SERVICE_WORKERS` |\n| --browser | browser or chrome channel to use, possible values: chrome, firefox, webkit, msedge.
*env* `PLAYWRIGHT_MCP_BROWSER` |\n| --caps | comma-separated list of additional capabilities to enable, possible values: vision, pdf, devtools.
*env* `PLAYWRIGHT_MCP_CAPS` |\n| --cdp-endpoint | CDP endpoint to connect to.
*env* `PLAYWRIGHT_MCP_CDP_ENDPOINT` |\n| --cdp-header | CDP headers to send with the connect request, multiple can be specified.
*env* `PLAYWRIGHT_MCP_CDP_HEADERS` |\n| --cdp-timeout | timeout in milliseconds for connecting to CDP endpoint, defaults to 30000ms
*env* `PLAYWRIGHT_MCP_CDP_TIMEOUT` |\n| --codegen | specify the language to use for code generation, possible values: \"typescript\", \"python\", \"java\", \"csharp\", \"none\". Default is \"typescript\".
*env* `PLAYWRIGHT_MCP_CODEGEN` |\n| --config | path to the configuration file.
*env* `PLAYWRIGHT_MCP_CONFIG` |\n| --console-level | level of console messages to return: \"error\", \"warning\", \"info\", \"debug\". Each level includes the messages of more severe levels.
*env* `PLAYWRIGHT_MCP_CONSOLE_LEVEL` |\n| --device | device to emulate, for example: \"iPhone 15\"
*env* `PLAYWRIGHT_MCP_DEVICE` |\n| --mobile | emulate a generic mobile device (Pixel 10 for Chromium, iPhone 17 for WebKit). Mobile pages are usually lighter, which saves tokens. Cannot be combined with --device.
*env* `PLAYWRIGHT_MCP_MOBILE` |\n| --executable-path | path to the browser executable.
*env* `PLAYWRIGHT_MCP_EXECUTABLE_PATH` |\n| --extension | Connect to a running browser instance (Edge/Chrome only). Requires the \"Playwright Extension\" to be installed.
*env* `PLAYWRIGHT_MCP_EXTENSION` |\n| --endpoint | Bound browser endpoint to connect to.
*env* `PLAYWRIGHT_MCP_ENDPOINT` |\n| --grant-permissions | List of permissions to grant to the browser context, for example \"geolocation\", \"clipboard-read\", \"clipboard-write\".
*env* `PLAYWRIGHT_MCP_GRANT_PERMISSIONS` |\n| --headless | run browser in headless mode, headed by default
*env* `PLAYWRIGHT_MCP_HEADLESS` |\n| --host | host to bind server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.
*env* `PLAYWRIGHT_MCP_HOST` |\n| --ignore-https-errors | ignore https errors
*env* `PLAYWRIGHT_MCP_IGNORE_HTTPS_ERRORS` |\n| --init-page | path to TypeScript file to evaluate on Playwright page object
*env* `PLAYWRIGHT_MCP_INIT_PAGE` |\n| --init-script | path to JavaScript file to add as an initialization script. The script will be evaluated in every page before any of the page's scripts. Can be specified multiple times.
*env* `PLAYWRIGHT_MCP_INIT_SCRIPT` |\n| --isolated | keep the browser profile in memory, do not save it to disk.
*env* `PLAYWRIGHT_MCP_ISOLATED` |\n| --image-responses | whether to send image responses to the client. Can be \"allow\" or \"omit\", Defaults to \"allow\".
*env* `PLAYWRIGHT_MCP_IMAGE_RESPONSES` |\n| --no-sandbox | disable the sandbox for all process types that are normally sandboxed.
*env* `PLAYWRIGHT_MCP_NO_SANDBOX` |\n| --output-dir | path to the directory for output files.
*env* `PLAYWRIGHT_MCP_OUTPUT_DIR` |\n| --output-max-size | Threshold for evicting old output files, in bytes.
*env* `PLAYWRIGHT_MCP_OUTPUT_MAX_SIZE` |\n| --port | port to listen on for SSE transport.
*env* `PLAYWRIGHT_MCP_PORT` |\n| --proxy-bypass | comma-separated domains to bypass proxy, for example \".com,chromium.org,.domain.com\"
*env* `PLAYWRIGHT_MCP_PROXY_BYPASS` |\n| --proxy-server | specify proxy server, for example \"http://myproxy:3128\" or \"socks5://myproxy:8080\"
*env* `PLAYWRIGHT_MCP_PROXY_SERVER` |\n| --sandbox | enable the sandbox for all process types that are normally not sandboxed.
*env* `PLAYWRIGHT_MCP_SANDBOX` |\n| --save-session | Whether to save the Playwright MCP session into the output directory.
*env* `PLAYWRIGHT_MCP_SAVE_SESSION` |\n| --secrets | path to a file containing secrets in the dotenv format
*env* `PLAYWRIGHT_MCP_SECRETS_FILE` |\n| --shared-browser-context | reuse the same browser context between all connected HTTP clients.
*env* `PLAYWRIGHT_MCP_SHARED_BROWSER_CONTEXT` |\n| --snapshot-boxes | include each element's bounding box as [box=x,y,width,height] in snapshots. Coordinates are viewport-relative, in CSS pixels.
*env* `PLAYWRIGHT_MCP_SNAPSHOT_BOXES` |\n| --snapshot-mode | when taking snapshots for responses, specifies the mode to use. Can be \"full\" or \"none\". Default is \"full\".
*env* `PLAYWRIGHT_MCP_SNAPSHOT_MODE` |\n| --storage-state | path to the storage state file for isolated sessions.
*env* `PLAYWRIGHT_MCP_STORAGE_STATE` |\n| --test-id-attribute | specify the attribute to use for test ids, defaults to \"data-testid\"
*env* `PLAYWRIGHT_MCP_TEST_ID_ATTRIBUTE` |\n| --timeout-action | specify action timeout in milliseconds, defaults to 5000ms
*env* `PLAYWRIGHT_MCP_TIMEOUT_ACTION` |\n| --timeout-navigation | specify navigation timeout in milliseconds, defaults to 60000ms
*env* `PLAYWRIGHT_MCP_TIMEOUT_NAVIGATION` |\n| --timeout-settle | how long to wait after each action for triggered work to settle, in milliseconds, defaults to 500ms
*env* `PLAYWRIGHT_MCP_TIMEOUT_SETTLE` |\n| --user-agent | specify user agent string
*env* `PLAYWRIGHT_MCP_USER_AGENT` |\n| --user-data-dir | path to the user data directory. If not specified, a temporary directory will be created.
*env* `PLAYWRIGHT_MCP_USER_DATA_DIR` |\n| --viewport-size | specify browser viewport size in pixels, for example \"1280x720\"
*env* `PLAYWRIGHT_MCP_VIEWPORT_SIZE` |\n\n\n\n### User profile\n\nYou can run Playwright MCP with persistent profile like a regular browser (default), in isolated contexts for testing sessions, or connect to your existing browser using the browser extension.\n\n**Persistent profile**\n\nAll the logged in information will be stored in the persistent profile, you can delete it between sessions if you'd like to clear the offline state.\nPersistent profile is located at the following locations and you can override it with the `--user-data-dir` argument.\n\n```bash\n# Windows\n%USERPROFILE%\\AppData\\Local\\ms-playwright\\mcp-{channel}-{workspace-hash}\n\n# macOS\n- ~/Library/Caches/ms-playwright/mcp-{channel}-{workspace-hash}\n\n# Linux\n- ~/.cache/ms-playwright/mcp-{channel}-{workspace-hash}\n```\n\n`{workspace-hash}` is derived from the MCP client's workspace root, so different projects get separate profiles automatically.\n\n> [!IMPORTANT]\n> A persistent profile can only be used by one browser instance at a time, so concurrent MCP clients sharing the same workspace will conflict. To run several clients in parallel, start each additional client with `--isolated` or point it at a distinct `--user-data-dir`.\n\n**Isolated**\n\nIn the isolated mode, each session is started in the isolated profile. Every time you ask MCP to close the browser,\nthe session is closed and all the storage state for this session is lost. You can provide initial storage state\nto the browser via the config's `contextOptions` or via the `--storage-state` argument. Learn more about the storage\nstate [here](https://playwright.dev/docs/auth).\n\n```js\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"npx\",\n \"args\": [\n \"@playwright/mcp@latest\",\n \"--isolated\",\n \"--storage-state={path/to/storage.json}\"\n ]\n }\n }\n}\n```\n\n**Browser Extension**\n\nThe Playwright MCP Chrome Extension allows you to connect to existing browser tabs and leverage your logged-in sessions and browser state. See [microsoft/playwright › packages/extension](https://github.com/microsoft/playwright/tree/main/packages/extension#readme) for installation and setup instructions.\n\n### Initial state\n\nThere are multiple ways to provide the initial state to the browser context or a page.\n\nFor the storage state, you can either:\n- Start with a user data directory using the `--user-data-dir` argument. This will persist all browser data between the sessions.\n- Start with a storage state file using the `--storage-state` argument. This will load cookies and local storage from the file into an isolated browser context.\n\nFor the page state, you can use:\n\n- `--init-page` to point to a TypeScript file that will be evaluated on the Playwright page object. This allows you to run arbitrary code to set up the page.\n\n```ts\n// init-page.ts\nexport default async ({ page }) => {\n await page.context().grantPermissions(['geolocation']);\n await page.context().setGeolocation({ latitude: 37.7749, longitude: -122.4194 });\n await page.setViewportSize({ width: 1280, height: 720 });\n};\n```\n\n- `--init-script` to point to a JavaScript file that will be added as an initialization script. The script will be evaluated in every page before any of the page's scripts.\nThis is useful for overriding browser APIs or setting up the environment.\n\n```js\n// init-script.js\nwindow.isPlaywrightMCP = true;\n```\n\n### Configuration file\n\nThe Playwright MCP server can be configured using a JSON configuration file. You can specify the configuration file\nusing the `--config` command line option:\n\n```bash\nnpx @playwright/mcp@latest --config path/to/config.json\n```\n\n

Configuration file schema

\n\n\n\n```typescript\n{\n /**\n * The browser to use.\n */\n browser?: {\n /**\n * The type of browser to use.\n */\n browserName?: 'chromium' | 'firefox' | 'webkit';\n\n /**\n * Keep the browser profile in memory, do not save it to disk.\n */\n isolated?: boolean;\n\n /**\n * Path to a user data directory for browser profile persistence.\n * Temporary directory is created by default.\n */\n userDataDir?: string;\n\n /**\n * Launch options passed to\n * @see https://playwright.dev/docs/api/class-browsertype#browser-type-launch-persistent-context\n *\n * This is useful for settings options like `channel`, `headless`, `executablePath`, etc.\n */\n launchOptions?: playwright.LaunchOptions;\n\n /**\n * Context options for the browser context.\n *\n * This is useful for settings options like `viewport`.\n */\n contextOptions?: playwright.BrowserContextOptions;\n\n /**\n * Chrome DevTools Protocol endpoint to connect to an existing browser instance in case of Chromium family browsers.\n */\n cdpEndpoint?: string;\n\n /**\n * CDP headers to send with the connect request.\n */\n cdpHeaders?: Record;\n\n /**\n * Timeout in milliseconds for connecting to CDP endpoint. Defaults to 30000 (30 seconds). Pass 0 to disable timeout.\n */\n cdpTimeout?: number;\n\n /**\n * Remote endpoint to connect to an existing Playwright server. May be a\n * WebSocket URL string, or a [ConnectOptions] object that mirrors the\n * `connectOptions` shape used by the test runner. When passed as an object,\n * `exposeNetwork`, `headers`, `slowMo`, and `timeout` are forwarded to the\n * underlying connect call.\n */\n remoteEndpoint?: string | playwright.ConnectOptions & { endpoint: string };\n\n /**\n * Paths to TypeScript files to add as initialization scripts for Playwright page.\n */\n initPage?: string[];\n\n /**\n * Paths to JavaScript files to add as initialization scripts.\n * The scripts will be evaluated in every page before any of the page's scripts.\n */\n initScript?: string[];\n },\n\n /**\n * Connect to a running browser instance (Edge/Chrome only). If specified, `browser`\n * config is ignored.\n * Requires the \"Playwright Extension\" to be installed.\n */\n extension?: boolean;\n\n server?: {\n /**\n * The port to listen on for SSE or MCP transport.\n */\n port?: number;\n\n /**\n * The host to bind the server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.\n */\n host?: string;\n\n /**\n * The hosts this server is allowed to serve from. Defaults to the host server is bound to.\n * This is not for CORS, but rather for the DNS rebinding protection.\n */\n allowedHosts?: string[];\n },\n\n /**\n * List of enabled tool capabilities. Possible values:\n * - 'core': Core browser automation features.\n * - 'pdf': PDF generation and manipulation.\n * - 'vision': Coordinate-based interactions.\n * - 'devtools': Developer tools features.\n */\n capabilities?: ToolCapability[];\n\n /**\n * Whether to save the Playwright session into the output directory.\n */\n saveSession?: boolean;\n\n /**\n * Reuse the same browser context between all connected HTTP clients.\n */\n sharedBrowserContext?: boolean;\n\n /**\n * Secrets are used to replace matching plain text in the tool responses to prevent the LLM\n * from accidentally getting sensitive data. It is a convenience and not a security feature,\n * make sure to always examine information coming in and from the tool on the client.\n */\n secrets?: Record;\n\n /**\n * The directory to save output files.\n */\n outputDir?: string;\n\n /**\n * Threshold for evicting old output files, in bytes.\n */\n outputMaxSize?: number;\n\n console?: {\n /**\n * The level of console messages to return. Each level includes the messages of more severe levels. Defaults to \"info\".\n */\n level?: 'error' | 'warning' | 'info' | 'debug';\n },\n\n network?: {\n /**\n * List of origins to allow the browser to request. Default is to allow all. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.\n *\n * Supported formats:\n * - Full origin: `https://example.com:8080` - matches only that origin\n * - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol\n */\n allowedOrigins?: string[];\n\n /**\n * List of origins to block the browser to request. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.\n *\n * Supported formats:\n * - Full origin: `https://example.com:8080` - matches only that origin\n * - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol\n */\n blockedOrigins?: string[];\n };\n\n /**\n * Specify the attribute to use for test ids, defaults to \"data-testid\".\n */\n testIdAttribute?: string;\n\n timeouts?: {\n /*\n * Configures default action timeout: https://playwright.dev/docs/api/class-page#page-set-default-timeout. Defaults to 5000ms.\n */\n action?: number;\n\n /*\n * Configures default navigation timeout: https://playwright.dev/docs/api/class-page#page-set-default-navigation-timeout. Defaults to 60000ms.\n */\n navigation?: number;\n\n /**\n * Configures default expect timeout: https://playwright.dev/docs/test-timeouts#expect-timeout. Defaults to 5000ms.\n */\n expect?: number;\n\n /**\n * How long to wait after each action for triggered work (navigations, requests) to settle before responding. Defaults to 500ms.\n */\n settle?: number;\n };\n\n /**\n * Whether to send image responses to the client. Can be \"allow\", \"omit\", or \"auto\". Defaults to \"auto\", which sends images if the client can display them.\n */\n imageResponses?: 'allow' | 'omit';\n\n snapshot?: {\n /**\n * When taking snapshots for responses, specifies the mode to use.\n */\n mode?: 'full' | 'none';\n\n /**\n * Whether to include each element's bounding box as [box=x,y,width,height] in snapshots.\n * Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect).\n */\n boxes?: boolean;\n };\n\n /**\n * allowUnrestrictedFileAccess acts as a guardrail to prevent the LLM from accidentally\n * wandering outside its intended workspace. It is a convenience defense to catch unintended\n * file access, not a secure boundary; a deliberate attempt to reach other directories can be\n * easily worked around, so always rely on client-level permissions for true security.\n */\n allowUnrestrictedFileAccess?: boolean;\n\n /**\n * Specify the language to use for code generation.\n */\n codegen?: 'typescript' | 'python' | 'java' | 'csharp' | 'none';\n}\n```\n\n\n\n

\n\n### Standalone MCP server\n\nWhen running headed browser on system w/o display or from worker processes of the IDEs,\nrun the MCP server from environment with the DISPLAY and pass the `--port` flag to enable HTTP transport.\n\n```bash\nnpx @playwright/mcp@latest --port 8931\n```\n\nAnd then in MCP client config, set the `url` to the HTTP endpoint:\n\n```js\n{\n \"mcpServers\": {\n \"playwright\": {\n \"url\": \"http://localhost:8931/mcp\"\n }\n }\n}\n```\n\n## Security\n\nPlaywright MCP is **not** a security boundary. See [MCP Security Best Practices](https://modelcontextprotocol.io/docs/tutorials/security/security_best_practices) for guidance on securing your deployment.\n\n

Docker

\n\n**NOTE:** The Docker implementation only supports headless chromium at the moment.\n\n```js\n{\n \"mcpServers\": {\n \"playwright\": {\n \"command\": \"docker\",\n \"args\": [\"run\", \"-i\", \"--rm\", \"--init\", \"--pull=always\", \"mcr.microsoft.com/playwright/mcp\"]\n }\n }\n}\n```\n\nOr If you prefer to run the container as a long-lived service instead of letting the MCP client spawn it, use:\n\n```\ndocker run -d -i --rm --init --pull=always \\\n --entrypoint node \\\n --name playwright \\\n -p 8931:8931 \\\n mcr.microsoft.com/playwright/mcp \\\n /app/cli.js --headless --browser chromium --no-sandbox --port 8931 --host 0.0.0.0\n```\n\nThe server will listen on host port **8931** and can be reached by any MCP client. \n\nYou can build the Docker image yourself.\n\n```\ndocker build -t mcr.microsoft.com/playwright/mcp .\n```\n

\n\n

Programmatic usage

\n\n```js\nimport http from 'http';\n\nimport { createConnection } from '@playwright/mcp';\nimport { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';\n\nhttp.createServer(async (req, res) => {\n // ...\n\n // Creates a headless Playwright MCP server with SSE transport\n const connection = await createConnection({ browser: { launchOptions: { headless: true } } });\n const transport = new SSEServerTransport('/messages', res);\n await connection.connect(transport);\n\n // ...\n});\n```\n

\n\n### Tools\n\n\n\n

Core automation

\n\n\n\n- **browser_click**\n - Title: Click\n - Description: Perform click on a web page\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `doubleClick` (boolean, optional): Whether to perform a double click instead of a single click\n - `button` (string, optional): Button to click, defaults to left\n - `modifiers` (array, optional): Modifier keys to press\n - Read-only: **false**\n\n\n\n- **browser_close**\n - Title: Close browser\n - Description: Close the page\n - Parameters: None\n - Read-only: **false**\n\n\n\n- **browser_console_messages**\n - Title: Get console messages\n - Description: Returns all console messages\n - Parameters:\n - `level` (string): Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to \"info\".\n - `all` (boolean, optional): Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false.\n - `filename` (string, optional): Filename to save the console messages to. If not provided, messages are returned as text.\n - Read-only: **true**\n\n\n\n- **browser_drag**\n - Title: Drag mouse\n - Description: Perform drag and drop between two elements\n - Parameters:\n - `startElement` (string, optional): Human-readable source element description used to obtain the permission to interact with the element\n - `startTarget` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `endElement` (string, optional): Human-readable target element description used to obtain the permission to interact with the element\n - `endTarget` (string): Exact target element reference from the page snapshot, or a unique element selector\n - Read-only: **false**\n\n\n\n- **browser_drop**\n - Title: Drop files or data onto an element\n - Description: Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of \"paths\" or \"data\" must be provided.\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `paths` (array, optional): Absolute paths to files to drop onto the element.\n - `data` (object, optional): Data to drop, as a map of MIME type to string value (e.g. {\"text/plain\": \"hello\", \"text/uri-list\": \"https://example.com\"}).\n - Read-only: **false**\n\n\n\n- **browser_evaluate**\n - Title: Evaluate JavaScript\n - Description: Evaluate JavaScript expression on page or element\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string, optional): Exact target element reference from the page snapshot, or a unique element selector\n - `function` (string): () => { /* code */ } or (element) => { /* code */ } when element is provided\n - `filename` (string, optional): Filename to save the result to. If not provided, result is returned as text.\n - Read-only: **false**\n\n\n\n- **browser_file_upload**\n - Title: Upload files\n - Description: Upload one or multiple files\n - Parameters:\n - `paths` (array, optional): The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.\n - Read-only: **false**\n\n\n\n- **browser_fill_form**\n - Title: Fill form\n - Description: Fill multiple form fields\n - Parameters:\n - `fields` (array): Fields to fill in\n - Read-only: **false**\n\n\n\n- **browser_find**\n - Title: Find in page snapshot\n - Description: Search the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context (like search snippets), each shown under its path from the root of the tree, which is cheaper than capturing the whole snapshot when you only need to locate an element and its ref.\n - Parameters:\n - `text` (string, optional): Plain text to search for in the page snapshot (case-insensitive substring match). Provide either text or regex, not both.\n - `regex` (string, optional): Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. \"/error/i\" for case-insensitive. Provide either text or regex, not both.\n - Read-only: **true**\n\n\n\n- **browser_handle_dialog**\n - Title: Handle a dialog\n - Description: Handle a dialog\n - Parameters:\n - `accept` (boolean): Whether to accept the dialog.\n - `promptText` (string, optional): The text of the prompt in case of a prompt dialog.\n - Read-only: **false**\n\n\n\n- **browser_hover**\n - Title: Hover mouse\n - Description: Hover over element on page\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - Read-only: **false**\n\n\n\n- **browser_navigate**\n - Title: Navigate to a URL\n - Description: Navigate to a URL\n - Parameters:\n - `url` (string): The URL to navigate to\n - Read-only: **false**\n\n\n\n- **browser_navigate_back**\n - Title: Go back\n - Description: Go back to the previous page in the history\n - Parameters: None\n - Read-only: **false**\n\n\n\n- **browser_network_request**\n - Title: Show network request details\n - Description: Returns full details (headers and body) of a single network request, or a single part if `part` is set. Use the number from browser_network_requests.\n - Parameters:\n - `index` (integer): 1-based index of the request, as printed by browser_network_requests.\n - `part` (string, optional): Return only this part of the request. Omit to return full details.\n - `filename` (string, optional): Filename to save the result to. If not provided, output is returned as text.\n - Read-only: **true**\n\n\n\n- **browser_network_requests**\n - Title: List network requests\n - Description: Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details.\n - Parameters:\n - `static` (boolean): Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false.\n - `filter` (string, optional): Only return requests whose URL matches this regexp (e.g. \"/api/.*user\").\n - `filename` (string, optional): Filename to save the network requests to. If not provided, requests are returned as text.\n - Read-only: **true**\n\n\n\n- **browser_press_key**\n - Title: Press a key\n - Description: Press a key on the keyboard\n - Parameters:\n - `key` (string): Name of the key to press or a character to generate, such as `ArrowLeft` or `a`\n - Read-only: **false**\n\n\n\n- **browser_resize**\n - Title: Resize browser window\n - Description: Resize the browser window\n - Parameters:\n - `width` (number): Width of the browser window\n - `height` (number): Height of the browser window\n - Read-only: **false**\n\n\n\n- **browser_run_code_unsafe**\n - Title: Run Playwright code (unsafe)\n - Description: Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent.\n - Parameters:\n - `code` (string, optional): A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: `async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }`\n - `filename` (string, optional): Load code from the specified file. If both code and filename are provided, code will be ignored.\n - Read-only: **false**\n\n\n\n- **browser_select_option**\n - Title: Select option\n - Description: Select an option in a dropdown\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `values` (array): Array of values to select in the dropdown. This can be a single value or multiple values.\n - Read-only: **false**\n\n\n\n- **browser_snapshot**\n - Title: Page snapshot\n - Description: Capture accessibility snapshot of the current page, this is better than screenshot\n - Parameters:\n - `target` (string, optional): Exact target element reference from the page snapshot, or a unique element selector\n - `filename` (string, optional): Save snapshot to markdown file instead of returning it in the response.\n - `depth` (number, optional): Limit the depth of the snapshot tree\n - `boxes` (boolean, optional): Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect)\n - Read-only: **true**\n\n\n\n- **browser_take_screenshot**\n - Title: Take a screenshot\n - Description: Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string, optional): Exact target element reference from the page snapshot, or a unique element selector\n - `type` (string, optional): Image format for the screenshot. If unset, inferred from the filename extension, otherwise png.\n - `filename` (string, optional): File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg|webp}` if not specified. Prefer relative file names to stay within the output directory.\n - `fullPage` (boolean, optional): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.\n - `scale` (string): Image resolution scale. \"css\" produces a screenshot sized in CSS pixels (smaller, consistent across devices). \"device\" produces a high-resolution screenshot using device pixels (larger, accounts for the device pixel ratio). Default is css.\n - Read-only: **true**\n\n\n\n- **browser_type**\n - Title: Type text\n - Description: Type text into editable element\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `text` (string): Text to type into the element\n - `submit` (boolean, optional): Whether to submit entered text (press Enter after)\n - `slowly` (boolean, optional): Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.\n - Read-only: **false**\n\n\n\n- **browser_wait_for**\n - Title: Wait for\n - Description: Wait for text to appear or disappear or a specified time to pass\n - Parameters:\n - `time` (number, optional): The time to wait in seconds\n - `text` (string, optional): The text to wait for\n - `textGone` (string, optional): The text to wait for to disappear\n - Read-only: **false**\n\n

\n\n

Tab management

\n\n\n\n- **browser_tabs**\n - Title: Manage tabs\n - Description: List, create, close, or select a browser tab.\n - Parameters:\n - `action` (string): Operation to perform\n - `index` (number, optional): Tab index, used for close/select. If omitted for close, current tab is closed.\n - `url` (string, optional): URL to navigate to in the new tab, used for new.\n - Read-only: **false**\n\n

\n\n

Browser installation

\n\n

Configuration (opt-in via --caps=config)

\n\n\n\n- **browser_get_config**\n - Title: Get config\n - Description: Get the final resolved config after merging CLI options, environment variables and config file.\n - Parameters: None\n - Read-only: **true**\n\n

\n\n

Network (opt-in via --caps=network)

\n\n\n\n- **browser_network_state_set**\n - Title: Set network state\n - Description: Sets the browser network state to online or offline. When offline, all network requests will fail.\n - Parameters:\n - `state` (string): Set to \"offline\" to simulate offline mode, \"online\" to restore network connectivity\n - Read-only: **false**\n\n\n\n- **browser_route**\n - Title: Mock network requests\n - Description: Set up a route to mock network requests matching a URL pattern\n - Parameters:\n - `pattern` (string): URL pattern to match (e.g., \"**/api/users\", \"**/*.{png,jpg}\")\n - `status` (number, optional): HTTP status code to return (default: 200)\n - `body` (string, optional): Response body (text or JSON string)\n - `contentType` (string, optional): Content-Type header (e.g., \"application/json\", \"text/html\")\n - `headers` (array, optional): Headers to add in \"Name: Value\" format\n - `removeHeaders` (string, optional): Comma-separated list of header names to remove from request\n - Read-only: **false**\n\n\n\n- **browser_route_list**\n - Title: List network routes\n - Description: List all active network routes\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_unroute**\n - Title: Remove network routes\n - Description: Remove network routes matching a pattern (or all routes if no pattern specified)\n - Parameters:\n - `pattern` (string, optional): URL pattern to unroute (omit to remove all routes)\n - Read-only: **false**\n\n

\n\n

Storage (opt-in via --caps=storage)

\n\n\n\n- **browser_cookie_clear**\n - Title: Clear cookies\n - Description: Clear all cookies\n - Parameters: None\n - Read-only: **false**\n\n\n\n- **browser_cookie_delete**\n - Title: Delete cookie\n - Description: Delete a specific cookie\n - Parameters:\n - `name` (string): Cookie name to delete\n - Read-only: **false**\n\n\n\n- **browser_cookie_get**\n - Title: Get cookie\n - Description: Get a specific cookie by name\n - Parameters:\n - `name` (string): Cookie name to get\n - Read-only: **true**\n\n\n\n- **browser_cookie_list**\n - Title: List cookies\n - Description: List all cookies (optionally filtered by domain/path)\n - Parameters:\n - `domain` (string, optional): Filter cookies by domain\n - `path` (string, optional): Filter cookies by path\n - Read-only: **true**\n\n\n\n- **browser_cookie_set**\n - Title: Set cookie\n - Description: Set a cookie with optional flags (domain, path, expires, httpOnly, secure, sameSite)\n - Parameters:\n - `name` (string): Cookie name\n - `value` (string): Cookie value\n - `domain` (string, optional): Cookie domain\n - `path` (string, optional): Cookie path\n - `expires` (number, optional): Cookie expiration as Unix timestamp\n - `httpOnly` (boolean, optional): Whether the cookie is HTTP only\n - `secure` (boolean, optional): Whether the cookie is secure\n - `sameSite` (string, optional): Cookie SameSite attribute\n - Read-only: **false**\n\n\n\n- **browser_localstorage_clear**\n - Title: Clear localStorage\n - Description: Clear all localStorage\n - Parameters: None\n - Read-only: **false**\n\n\n\n- **browser_localstorage_delete**\n - Title: Delete localStorage item\n - Description: Delete a localStorage item\n - Parameters:\n - `key` (string): Key to delete\n - Read-only: **false**\n\n\n\n- **browser_localstorage_get**\n - Title: Get localStorage item\n - Description: Get a localStorage item by key\n - Parameters:\n - `key` (string): Key to get\n - Read-only: **true**\n\n\n\n- **browser_localstorage_list**\n - Title: List localStorage\n - Description: List all localStorage key-value pairs\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_localstorage_set**\n - Title: Set localStorage item\n - Description: Set a localStorage item\n - Parameters:\n - `key` (string): Key to set\n - `value` (string): Value to set\n - Read-only: **false**\n\n\n\n- **browser_sessionstorage_clear**\n - Title: Clear sessionStorage\n - Description: Clear all sessionStorage\n - Parameters: None\n - Read-only: **false**\n\n\n\n- **browser_sessionstorage_delete**\n - Title: Delete sessionStorage item\n - Description: Delete a sessionStorage item\n - Parameters:\n - `key` (string): Key to delete\n - Read-only: **false**\n\n\n\n- **browser_sessionstorage_get**\n - Title: Get sessionStorage item\n - Description: Get a sessionStorage item by key\n - Parameters:\n - `key` (string): Key to get\n - Read-only: **true**\n\n\n\n- **browser_sessionstorage_list**\n - Title: List sessionStorage\n - Description: List all sessionStorage key-value pairs\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_sessionstorage_set**\n - Title: Set sessionStorage item\n - Description: Set a sessionStorage item\n - Parameters:\n - `key` (string): Key to set\n - `value` (string): Value to set\n - Read-only: **false**\n\n\n\n- **browser_set_storage_state**\n - Title: Restore storage state\n - Description: Restore storage state (cookies, local storage) from a file. This clears existing cookies and local storage before restoring.\n - Parameters:\n - `filename` (string): Path to the storage state file to restore from\n - Read-only: **false**\n\n\n\n- **browser_storage_state**\n - Title: Save storage state\n - Description: Save storage state (cookies, local storage) to a file for later reuse\n - Parameters:\n - `filename` (string, optional): File name to save the storage state to. Defaults to `storage-state-{timestamp}.json` if not specified.\n - Read-only: **true**\n\n

\n\n

DevTools (opt-in via --caps=devtools)

\n\n\n\n- **browser_annotate**\n - Title: Annotate the current page\n - Description: Open the Playwright Dashboard in annotation mode for the current page and wait for the user to draw annotations. Returns the annotated screenshot, ARIA snapshot, and the list of annotations.\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_hide_highlight**\n - Title: Hide element highlight\n - Description: Remove a highlight overlay previously added for the element.\n - Parameters:\n - `element` (string, optional): Human-readable element description used when adding the highlight; must match the value passed to browser_highlight.\n - `target` (string, optional): Exact target element reference from the page snapshot, or a unique element selector\n - Read-only: **true**\n\n\n\n- **browser_highlight**\n - Title: Highlight element\n - Description: Show a persistent highlight overlay around the element on the page.\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - `style` (string, optional): Additional inline CSS applied to the highlight overlay, e.g. \"outline: 2px dashed red\".\n - Read-only: **true**\n\n\n\n- **browser_resume**\n - Title: Resume paused script execution\n - Description: Resume script execution after it was paused. When called with step set to true, execution will pause again before the next action.\n - Parameters:\n - `step` (boolean, optional): When true, execution will pause again before the next action, allowing step-by-step debugging.\n - `location` (string, optional): Pause execution at a specific :, e.g. \"example.spec.ts:42\".\n - Read-only: **false**\n\n\n\n- **browser_start_tracing**\n - Title: Start tracing\n - Description: Start trace recording\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_start_video**\n - Title: Start video\n - Description: Start video recording\n - Parameters:\n - `filename` (string, optional): Filename to save the video.\n - `size` (object, optional): Video size\n - Read-only: **true**\n\n\n\n- **browser_stop_tracing**\n - Title: Stop tracing\n - Description: Stop trace recording\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_stop_video**\n - Title: Stop video\n - Description: Stop video recording\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_video_chapter**\n - Title: Video chapter\n - Description: Add a chapter marker to the video recording. Shows a full-screen chapter card with blurred backdrop.\n - Parameters:\n - `title` (string): Chapter title\n - `description` (string, optional): Chapter description\n - `duration` (number, optional): Duration in milliseconds to show the chapter card\n - Read-only: **true**\n\n\n\n- **browser_video_hide_actions**\n - Title: Hide action overlays\n - Description: Stop annotating actions performed on the page.\n - Parameters: None\n - Read-only: **true**\n\n\n\n- **browser_video_show_actions**\n - Title: Show action overlays\n - Description: Annotate subsequent actions performed on the page with a callout that names the action and highlights the target element. Useful while video recording or screencasting.\n - Parameters:\n - `duration` (number, optional): How long each action annotation stays on screen, in milliseconds. Defaults to 500.\n - `position` (string, optional): Where to place the action title relative to the page. Defaults to top-right.\n - `cursor` (string, optional): Cursor decoration for pointer actions. \"pointer\" (default) animates a mouse pointer from the previous action point to the next one; \"none\" disables the cursor decoration.\n - Read-only: **true**\n\n

\n\n

Coordinate-based (opt-in via --caps=vision)

\n\n\n\n- **browser_mouse_click_xy**\n - Title: Click\n - Description: Click mouse button at a given position\n - Parameters:\n - `x` (number): X coordinate\n - `y` (number): Y coordinate\n - `button` (string, optional): Button to click, defaults to left\n - `clickCount` (number, optional): Number of clicks, defaults to 1\n - `delay` (number, optional): Time to wait between mouse down and mouse up in milliseconds, defaults to 0\n - Read-only: **false**\n\n\n\n- **browser_mouse_down**\n - Title: Press mouse down\n - Description: Press mouse down\n - Parameters:\n - `button` (string, optional): Button to press, defaults to left\n - Read-only: **false**\n\n\n\n- **browser_mouse_drag_xy**\n - Title: Drag mouse\n - Description: Drag left mouse button to a given position\n - Parameters:\n - `startX` (number): Start X coordinate\n - `startY` (number): Start Y coordinate\n - `endX` (number): End X coordinate\n - `endY` (number): End Y coordinate\n - Read-only: **false**\n\n\n\n- **browser_mouse_move_xy**\n - Title: Move mouse\n - Description: Move mouse to a given position\n - Parameters:\n - `x` (number): X coordinate\n - `y` (number): Y coordinate\n - Read-only: **false**\n\n\n\n- **browser_mouse_up**\n - Title: Press mouse up\n - Description: Press mouse up\n - Parameters:\n - `button` (string, optional): Button to press, defaults to left\n - Read-only: **false**\n\n\n\n- **browser_mouse_wheel**\n - Title: Scroll mouse wheel\n - Description: Scroll mouse wheel\n - Parameters:\n - `deltaX` (number): X delta\n - `deltaY` (number): Y delta\n - Read-only: **false**\n\n

\n\n

PDF generation (opt-in via --caps=pdf)

\n\n\n\n- **browser_pdf_save**\n - Title: Save as PDF\n - Description: Save page as PDF\n - Parameters:\n - `filename` (string, optional): File name to save the pdf to. Defaults to `page-{timestamp}.pdf` if not specified. Prefer relative file names to stay within the output directory.\n - Read-only: **true**\n\n

\n\n

Test assertions (opt-in via --caps=testing)

\n\n\n\n- **browser_generate_locator**\n - Title: Create locator for element\n - Description: Generate locator for the given element to use in tests\n - Parameters:\n - `element` (string, optional): Human-readable element description used to obtain permission to interact with the element\n - `target` (string): Exact target element reference from the page snapshot, or a unique element selector\n - Read-only: **true**\n\n\n\n- **browser_verify_element_visible**\n - Title: Verify element visible\n - Description: Verify element is visible on the page\n - Parameters:\n - `role` (string): ROLE of the element. Can be found in the snapshot like this: `- {ROLE} \"Accessible Name\":`\n - `accessibleName` (string): ACCESSIBLE_NAME of the element. Can be found in the snapshot like this: `- role \"{ACCESSIBLE_NAME}\"`\n - Read-only: **false**\n\n\n\n- **browser_verify_list_visible**\n - Title: Verify list visible\n - Description: Verify list is visible on the page\n - Parameters:\n - `element` (string): Human-readable list description\n - `target` (string): Exact target element reference that points to the list\n - `items` (array): Items to verify\n - Read-only: **false**\n\n\n\n- **browser_verify_text_visible**\n - Title: Verify text visible\n - Description: Verify text is visible on the page. Prefer browser_verify_element_visible if possible.\n - Parameters:\n - `text` (string): TEXT to verify. Can be found in the snapshot like this: `- role \"Accessible Name\": {TEXT}` or like this: `- text: {TEXT}`\n - Read-only: **false**\n\n\n\n- **browser_verify_value**\n - Title: Verify value\n - Description: Verify element value\n - Parameters:\n - `type` (string): Type of the element\n - `element` (string): Human-readable element description\n - `target` (string): Exact target element reference from the page snapshot\n - `value` (string): Value to verify. For checkbox, use \"true\" or \"false\".\n - Read-only: **false**\n\n

\n\n\n\n","changelogMarkdown","videoKey","requiredSecretsJson","publishedAt","priceCents","trialDays",0,"iconType","image","upstream",{"_97":98,"_99":100,"_101":102,"_103":104,"_105":106,"_107":108},"requiredSecrets",[],"tags",[96],"assets",[],"stats",{"_94":81,"_95":81},"ratingAvg","reviewCount","playwright","topics",[114,96],"license","Apache-2.0","language","TypeScript","registryName","io.github.microsoft/playwright-mcp","homepage","https://www.npmjs.com/package/@playwright/mcp","packages",[109],{"_110":111,"_112":113,"_71":72},"registryType","npm","identifier","@playwright/mcp","mcp","ENV",{"_117":118,"_119":120,"_121":122},"ENVIRONMENT","production","TURNSTILE_SITE_KEY","0x4AAAAAAB8-rEI2gNDf_QhU","SENTRY_DSN","https://45fd1229f78089d5c3ee78be128030e1@o4510583261757440.ingest.de.sentry.io/4510584253448272"]