Chrome DevTools MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Set to * to enable verbose logs. Useful for submitting bug reports. | |
| channel | No | Specify a different Chrome channel that should be used. The default is the stable channel version. Choices: stable, canary, beta, dev | |
| logFile | No | Path to a file to write debug logs to. Set the env variable DEBUG to * to enable verbose logs. Useful for submitting bug reports. | |
| headless | No | Whether to run in headless (no UI) mode. | false |
| isolated | No | If specified, creates a temporary user-data-dir that is automatically cleaned up after the browser is closed. | false |
| viewport | No | Initial viewport size for the Chrome instances started by the server. For example, 1280x720. In headless mode, max size is 3840x2160px. | |
| chromeArg | No | Additional arguments for Chrome. Only applies when Chrome is launched by chrome-devtools-mcp. | |
| browserUrl | No | Connect to a running Chrome instance using port forwarding. For more details see: https://developer.chrome.com/docs/devtools/remote-debugging/local-server. | |
| proxyServer | No | Proxy server configuration for Chrome passed as --proxy-server when launching the browser. See https://www.chromium.org/developers/design-documents/network-settings/ for details. | |
| executablePath | No | Path to custom Chrome executable. | |
| acceptInsecureCerts | No | If enabled, ignores errors relative to self-signed and expired certificates. Use with caution. |
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 |
|---|---|
| list_console_messagesA | List all console messages for the currently selected page since the last navigation. |
| emulate_cpuB | Emulates CPU throttling by slowing down the selected page's execution. |
| emulate_networkA | Emulates network conditions such as throttling or offline mode on the selected page. |
| clickB | Clicks on the provided element |
| dragC | Drag an element onto another element |
| fillC | Type text into a input, text area or select an option from a element. |
| fill_formB | Fill out multiple form elements at once |
| hoverB | Hover over the provided element |
| upload_fileB | Upload a file through a provided element. |
| get_network_requestA | Gets a network request by URL. You can get all requests by calling list_network_requests. |
| list_network_requestsB | List all requests for the currently selected page since the last navigation. |
| close_pageA | Closes the page by its index. The last open page cannot be closed. |
| handle_dialogA | If a browser dialog was opened, use this command to handle it |
| list_pagesB | Get a list of pages open in the browser. |
| navigate_pageB | Navigates the currently selected page to a URL. |
| navigate_page_historyB | Navigates the currently selected page. |
| new_pageB | Creates a new page |
| 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. |
| performance_analyze_insightA | Provides more detailed information on a specific Performance Insight that was highlighted in the results of a trace recording. |
| performance_start_traceA | Starts a performance trace recording on the selected page. This can be used to look for performance problems and insights to improve the performance of the page. It will also report Core Web Vital (CWV) scores for the page. |
| performance_stop_traceA | Stops the active performance trace recording on the selected page. |
| take_screenshotB | Take a screenshot of the page or element. |
| evaluate_scriptA | Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON so returned values have to JSON-serializable. |
| take_snapshotA | Take a text snapshot of the currently selected page. The snapshot lists page elements along with a unique identifier (uid). Always use the latest snapshot. Prefer taking a snapshot over taking a screenshot. |
| wait_forB | 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 26 tools
Most tools have distinct purposes, but there is some overlap between 'navigate_page' and 'navigate_page_history' that could cause confusion. The descriptions clarify that 'navigate_page' goes to a URL while 'navigate_page_history' handles back/forward navigation, but the naming doesn't make this distinction obvious. Other tools like 'fill' and 'fill_form' are well-differentiated by scope.
The naming follows a consistent verb_noun pattern (e.g., 'click', 'close_page', 'drag') with clear, descriptive names. There are minor deviations like 'performance_analyze_insight' which uses a verb_verb_noun structure, but overall the pattern is predictable and readable across the set.
With 26 tools, the count is borderline high for a DevTools server, potentially feeling heavy but still manageable. It covers a broad range of browser automation tasks, which justifies the number, but it might overwhelm agents with too many options for basic operations.
The toolset provides comprehensive coverage for browser automation and DevTools functionality, including navigation, interaction, performance analysis, network monitoring, and debugging. There are no obvious gaps; it supports full lifecycle operations from page creation to performance tracing and element manipulation.