Playwright MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_codegen_sessionC | Start a new code generation session to record Playwright actions |
| end_codegen_sessionC | End a code generation session and generate the test file |
| get_codegen_sessionC | Get information about a code generation session |
| clear_codegen_sessionC | Clear a code generation session without generating a test |
| playwright_navigateC | Navigate to a URL |
| playwright_screenshotC | Take a screenshot of the current page or a specific element |
| playwright_clickC | Click an element on the page |
| playwright_iframe_clickC | Click an element in an iframe on the page |
| playwright_iframe_fillC | Fill an element in an iframe on the page |
| playwright_fillC | fill out an input field |
| playwright_selectC | Select an element on the page with Select tag |
| playwright_hoverC | Hover an element on the page |
| playwright_evaluateC | Execute JavaScript in the browser console |
| playwright_console_logsC | Retrieve console logs from the browser with filtering options |
| playwright_closeB | Close the browser and release all resources |
| playwright_getC | Perform an HTTP GET request |
| playwright_postC | Perform an HTTP POST request |
| playwright_putC | Perform an HTTP PUT request |
| playwright_patchC | Perform an HTTP PATCH request |
| playwright_deleteC | Perform an HTTP DELETE request |
| playwright_expect_responseB | Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait for its completion. |
| playwright_assert_responseB | Wait for and validate a previously initiated HTTP response wait operation. |
| playwright_custom_user_agentC | Set a custom User Agent for the browser |
| playwright_get_visible_textB | Get the visible text content of the current page |
| playwright_get_visible_htmlB | Get the HTML content of the current page |
| playwright_go_backB | Navigate back in browser history |
| playwright_go_forwardA | Navigate forward in browser history |
| playwright_dragC | Drag an element to a target location |
| playwright_press_keyC | Press a keyboard key |
| playwright_save_as_pdfC | Save the current page as a PDF file |
| playwright_click_and_switch_tabA | Click a link and switch to the newly opened tab |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Browser console logs |
TDQS
Scored across 31 tools
Most tools have distinct purposes, with clear separation between browser actions (e.g., click, fill, navigate), HTTP methods (get, post, put), and code generation sessions. However, some overlap exists between playwright_click and playwright_iframe_click, where the iframe variant is a specialized case rather than a fundamentally different operation, which could cause minor confusion.
Tool names follow a highly consistent snake_case pattern with clear verb_noun structures. Code generation tools use consistent 'codegen_session' terminology, while Playwright actions consistently start with 'playwright_' followed by descriptive verbs (e.g., playwright_click, playwright_navigate). This predictability makes the set easy to navigate and understand.
With 31 tools, the count feels heavy for a Playwright automation server, suggesting potential over-fragmentation. While Playwright is feature-rich, many tools could be consolidated (e.g., separate HTTP methods might be unified into a single playwright_request tool). The number is borderline excessive for typical agent workflows.
The toolset provides comprehensive coverage for Playwright automation, including navigation, interaction (click, fill, hover), HTTP requests, iframe handling, debugging (logs, screenshots), and code generation. It supports full CRUD-like operations for web testing without obvious gaps, enabling agents to handle complex browser automation tasks end-to-end.