Playwriter Browser MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | MCP HTTP 服务端口 | 3280 |
| OUTPUT_DIR | No | 截图、PDF、trace 文件输出目录 | ./output |
| PLAYWRITER_RELAY_HOST | No | Relay 地址 | 127.0.0.1 |
| PLAYWRITER_RELAY_PORT | No | Playwriter WebSocket relay 端口 | 19988 |
| PLAYWRITER_EXTENSION_ID | No | 多 Profile 时指定连接哪个扩展 | (自动检测) |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateB | Navigate to a URL |
| browser_navigate_backB | Go back to the previous page in the history |
| browser_snapshotA | Capture accessibility snapshot of the current page. Returns a text representation of the page with [ref] markers for interactive elements. Use these refs with other tools like browser_click. |
| browser_take_screenshotC | Take a screenshot of the current page |
| browser_clickA | Perform click on a web page element identified by its ref from a snapshot |
| browser_typeB | Type text into an editable element identified by ref |
| browser_press_keyB | Press a key on the keyboard. Use key names like 'ArrowLeft', 'Enter', 'Escape', 'a', 'Control+c', etc. |
| browser_hoverC | Hover over an element on the page |
| browser_dragC | Perform drag and drop between two elements |
| browser_select_optionB | Select an option in a dropdown |
| browser_fill_formB | Fill multiple form fields at once |
| browser_tabsB | List, create, close, or select a browser tab |
| browser_closeC | Close the current page |
| browser_wait_forC | Wait for text to appear or disappear, or wait for a specified time |
| browser_resizeB | Resize the browser window |
| browser_evaluateB | Evaluate JavaScript expression on the page or on a specific element |
| browser_run_codeA | Run a Playwright code snippet. The function receives |
| browser_console_messagesA | Returns console messages captured from the page. Each level includes more severe levels (error < warning < info < debug). |
| browser_network_requestsB | Returns network requests captured since page load |
| browser_file_uploadB | Upload one or multiple files to a file input element |
| browser_handle_dialogA | Handle a JavaScript dialog (alert, confirm, prompt). Dialogs are queued as they appear. This tool handles the most recent unhandled dialog. |
| browser_generate_locatorA | Generate a Playwright locator for an element (useful for writing tests) |
| browser_verify_element_visibleC | Verify an element is visible on the page |
| browser_verify_text_visibleC | Verify text is visible on the page |
| browser_verify_list_visibleB | Verify a list with specific items is visible on the page |
| browser_verify_valueC | Verify an element's value |
| browser_pdf_saveB | Save the current page as a PDF file |
| browser_start_tracingA | Start recording a Playwright trace. Stop with browser_stop_tracing to save the trace file. |
| browser_stop_tracingB | Stop trace recording and save the trace file |
| browser_resetA | Reset the browser connection. Use when tools fail with connection errors, page closed errors, or the browser becomes unresponsive. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/babelcloud/playwriter-browser-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server