chrome-devtools-mcp-mux
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_MUX_DEBUG | No | 1 logs every rewrite diff | |
| CDMCP_MUX_SOCKET | No | Override unix socket path for the daemon | |
| CDMCP_MUX_CHROMIUM | No | Chromium binary (defaults to bundled Puppeteer) | |
| CDMCP_MUX_HEADLESS | No | false makes Chrome visible (default: headless) | |
| CDMCP_MUX_USER_DATA_DIR | No | Override Chrome profile directory |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| clickB | Clicks on the provided element |
| close_pageB | Closes the page by its index. The last open page cannot be closed. |
| dragB | Drag an element onto another element |
| emulateC | Emulates various features on the selected page. |
| evaluate_scriptA | Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON, so returned values have to be JSON-serializable. |
| fillA | Type text into an input, text area or select an option from a element. |
| fill_formB | Fill out multiple form elements at once |
| get_console_messageA | Gets a console message by its ID. You can get all messages by calling list_console_messages. |
| get_network_requestA | Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel. |
| handle_dialogA | If a browser dialog was opened, use this command to handle it |
| hoverB | Hover over the provided element |
| lighthouse_auditA | Get Lighthouse score and reports for accessibility, SEO and best practices. This excludes performance. For performance audits, run performance_start_trace |
| list_console_messagesA | List all console messages for the currently selected page since the last navigation. |
| list_network_requestsA | List all requests for the currently selected page since the last navigation. |
| list_pagesA | Get a list of pages open in the browser. |
| navigate_pageA | Go to a URL, or back, forward, or reload. Use project URL if not specified otherwise. |
| new_pageB | Open a new tab and load a URL. Use project URL if not specified otherwise. |
| performance_analyze_insightA | Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording. |
| performance_start_traceA | Start a performance trace on the selected webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed. |
| performance_stop_traceA | Stop the active performance trace recording on the selected webpage. |
| press_keyA | Press a key or key combination. Use this when other input methods like fill() cannot be used (e.g., keyboard shortcuts, navigation keys, or special key combinations). |
| resize_pageA | Resizes the selected page's window so that the page has specified dimension |
| select_pageA | Select a page as a context for future tool calls. |
| take_memory_snapshotA | Capture a heap snapshot of the currently selected page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks. |
| take_screenshotB | Take a screenshot of the page or element. |
| take_snapshotA | Take a text snapshot of the currently selected page based on the a11y tree. The snapshot lists page elements along with a unique identifier (uid). Always use the latest snapshot. Prefer taking a snapshot over taking a screenshot. The snapshot indicates the element selected in the DevTools Elements panel (if any). |
| type_textA | Type text using keyboard into a previously focused input |
| upload_fileB | Upload a file through a provided element. |
| wait_forA | Wait for the specified text to appear on the selected page. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 29 tools
Tools have distinct purposes: interaction (click, drag, fill), page management (new_page, close_page), and diagnostics (performance, console, network). Some overlap exists between fill, type_text, and press_key, but descriptions clarify their specific use cases. Snapshot vs screenshot are clearly differentiated.
All tools follow a consistent verb_noun snake_case pattern (e.g., list_console_messages, take_screenshot, performance_start_trace). No mixed conventions or vague verbs like 'process' or 'do_thing' are present.
29 tools is on the higher end but appropriate given the broad scope of Chrome DevTools functionality covered (interaction, performance, network, memory). Each tool serves a distinct need, and the count is justified even if slightly above the typical 15-tool comfort zone.
The surface covers core DevTools workflows: page navigation, element interaction, script evaluation, console/network inspection, performance tracing, and screenshots. Minor gaps exist (e.g., cookie management, network interception) but can be worked around via evaluate_script.