chrome-devtools · chromedevtools — Claude Code skill: setup and use
This skill connects Chrome DevTools through MCP for page debugging, browser automation, performance checks, and network inspection.
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a claude-codeWhat chrome-devtools does
The skill runs Chrome DevTools through MCP and lets Claude Code work with web pages. Chrome starts on the first tool call and uses a persistent profile. Check available launch options with npx chrome-devtools-mcp@latest --help.
A typical flow is to open a page with navigate_page or new_page, wait with wait_for, inspect the structure through take_snapshot, then interact using element uids. Use take_screenshot for visual checks, get_css_styles for matched CSS rules and variables, and evaluate_script for DOM or JavaScript data that the other tools do not expose.
Page-scoped tools require a pageId from new_page or list_pages. Extension tools are available only when the MCP server starts with --categoryExtensions; memory debugging uses --memoryDebugging. Check that MCP configuration before testing an extension.
What it helps with
- debug a web page with Chrome DevTools
- automate browser navigation and interactions
- inspect an element's DOM and CSS
- trace network requests and page performance
- test a browser extension
Example prompts for the agent
- Open the page with `new_page`, wait for it to load, take a structure snapshot, and click the element with the required `uid`.
- Inspect this element with `get_css_styles`, then explain why its style is not applied.
- Review the page's network requests and find the request that failed.
How to install chrome-devtools
1Skills CLI (Vercel)
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a claude-code2Manually: put the files in place
~/.claude/skills/chrome-devtools/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/chrome-devtools/
1Skills CLI (Vercel)
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a codex2Manually: put the files in place
.agents/skills/chrome-devtools/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a cursor2Manually: put the files in place
.cursor/skills/chrome-devtools/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ChromeDevTools/chrome-devtools-mcp chrome-devtools2Manually: put the files in place
.github/skills/chrome-devtools/SKILL.md1Skills CLI (Vercel)
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a gemini-cli2Platform CLI
gemini skills install https://github.com/ChromeDevTools/chrome-devtools-mcp --path skills/chrome-devtoolsManually: put the files in place
.devin/skills/chrome-devtools/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set6
The whole set →Other versions of chrome-devtools
Similar
Questions about chrome-devtools
How do I install chrome-devtools in Claude Code?
Run npx skills add ChromeDevTools/chrome-devtools-mcp --skill chrome-devtools -a claude-code, then run the same command again. The skill file is at ~/.claude/skills/chrome-devtools/SKILL.md.
What does chrome-devtools do?
The skill connects Chrome DevTools through MCP. It can open pages, interact with elements, inspect CSS, read DOM data, and analyze browser behavior.
What is required to test extensions?
Start the MCP server with --categoryExtensions, then restart the MCP server or AI client. Use --memoryDebugging for memory debugging.
Source text
SKILL.md · Apache-2.0
---
name: chrome-devtools
description: Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).
---
## Core Concepts
**Browser lifecycle**: Browser starts automatically on first tool call using a persistent Chrome profile. Configure via CLI args in the MCP server configuration: `npx chrome-devtools-mcp@latest --help`.
Addional tooling can be enabled by providing the following flags:
- For extension tooling, use the `--categoryExtensions` flag.
- For memory tooling, use the `--memoryDebugging` flag.
**Page targeting**: Page-scoped tools require a `pageId` parameter to target a specific page. Use `list_pages` to see available pages and their IDs (e.g. `pageId: 1`), or use the ID returned when creating a page with `new_page`.
Note: For `evaluate_script`, `pageId` is required when targeting pages. However, when `--categoryExtensions` is enabled, `pageId` is optional so you can pass `serviceWorkerId` instead to evaluate inside an extension background service worker.
**Element interaction**: Use `take_snapshot` to get page structure with element `uid`s. Each element has a unique `uid` for interaction. If an element isn't found, take a fresh snapshot - the element may have been removed or the page changed.
## Workflow Patterns
### Before interacting with a page
1. Navigate: `navigate_page` or `new_page`
2. Wait: `wait_for` to ensure content is loaded if you know what you look for.
3. Snapshot: `take_snapshot` with `pageId` to understand page structure
4. Interact: Use element `uid`s from snapshot for `click`, `fill`, etc., passing the corresponding `pageId`.
### Efficient data retrieval
- Use `filePath` parameter for large outputs (screenshots, snapshots, traces)
- Use pagination (`pageIdx`, `pageSize`) and filtering (`types`) to minimize data
- Set `includeSnapshot: false` on input actions unless you need updated page state
### Tool selection
- **Automation/interaction**: `take_snapshot` (text-based, faster, better for automation)
- **Visual inspection**: `take_screenshot` (when user needs to see visual state)
- **CSS & Styling inspection**: Use `get_css_styles` to inspect matched rules, cascade, and CSS variables. Treat the output as authoritative and complete.
- **Additional details**: Use `evaluate_script` for runtime DOM/JS data not available via `get_css_styles` or `take_snapshot`.
### Parallel execution
You can send multiple tool calls in parallel, but maintain correct order: navigate → wait → snapshot → interact.
### Testing an extension
> **Before proceeding**: Extension tools (`install_extension`, `list_extensions`, etc.) are only available when the MCP server is started with the `--categoryExtensions` flag. If these tools are not in your tool list, stop and ask the user to update their MCP server configuration:
>
> ```json
> {
> "mcpServers": {
> "chrome-devtools": {
> "command": "npx",
> "args": ["chrome-devtools-mcp@latest", "--categoryExtensions"]
> }
> }
> }
> ```
>
> After updating, the user must restart the MCP server (or their AI client) for the change to take effect.
1. **Install**: Use `install_extension` with the path to the unpacked extension.
2. **Identify**: Get the extension ID from the response or by calling `list_extensions`.
3. **Trigger Action**: Use `trigger_extension_action` to open the popup or side panel if applicable.
4. **Verify Service Worker**: Use `evaluate_script` with `serviceWorkerId` (omitting `pageId` and `args`) to check extension state or trigger background actions. When evaluating in a page, pass `pageId` (omitting `serviceWorkerId`).
5. **Verify Page Behavior**: Navigate to a page where the extension operates and use `take_snapshot` to check if content scripts injected elements or modified the page correctly.
## Troubleshooting
If `chrome-devtools-mcp` is insufficient, guide users to use Chrome DevTools UI:
- https://developer.chrome.com/docs/devtools
- https://developer.chrome.com/docs/devtools/ai-assistance
If there are errors launching `chrome-devtools-mcp` or Chrome, refer to https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/main/docs/troubleshooting.md.
© ChromeDevTools · Apache-2.0 · ChromeDevTools/chrome-devtools-mcp