Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/triuzzi/brave-devtools-mcp/brave-devtools-clinpx skills add triuzzi/brave-devtools-mcp --skill brave-devtools-cligit clone --depth 1 https://github.com/triuzzi/brave-devtools-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.02824 |
| Opus 5 | $0.00016 | $0.01412 |
| Sonnet 5 | $0.00006 | $0.00565 |
| Haiku 4.5 | $0.00003 | $0.00282 |
Grade A, and why
brave-devtools-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to chrome-devtools-cli — 200 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The brave-mcp CLI lets you interact with the browser from your terminal.
Setup
Note: If this is your very first time using the CLI, see references/installation.md for setup. Installation is a one-time prerequisite and is not part of the regular AI workflow.
AI Workflow
- Execute: Run tools directly. If you don't know the target page's ID, run
brave-devtools list_pagesto find it. The background server starts implicitly; do not runstart/status/stopbefore each use. - Inspect: Use
brave-devtools take_snapshot <pageId>to get an element<uid>. - Act: Use
brave-devtools click <pageId> <uid>,brave-devtools fill <pageId> <uid> <value>, etc. State persists across commands.
Snapshot example:
uid=1_0 RootWebArea "Example Domain" url="https://example.com/"
uid=1_1 heading "Example Domain" level="1"
Permissions & File Access
By default, the CLI has full filesystem access (--allowUnrestrictedPaths=true), allowing file-saving parameters (--filePath, --outputDirPath) and upload_file to access files anywhere on the system. Pass --allowUnrestrictedPaths=false if you want to restrict file access to the OS temp directory.
Command Usage
brave-devtools <tool> [arguments] [flags]
- Required arguments are passed positionally; optional arguments use flags.
- Use
--helpon any command for usage details. - Output defaults to plain Markdown-like text; pass
--output-format=jsonfor JSON.
Input Automation ( from snapshot)
brave-devtools take_snapshot 1 # Take a text snapshot of the page to get UIDs for elements
brave-devtools click 1 "id" # Clicks on the provided element
brave-devtools click 1 "id" --dblClick true --includeSnapshot true # Double clicks and returns a snapshot
brave-devtools drag 1 "src" "dst" # Drag an element onto another element
brave-devtools drag 1 "src" "dst" --includeSnapshot true # Drag an element and return a snapshot
brave-devtools fill 1 "id" "text" # Type text into an input, textarea, or select an option
brave-devtools fill 1 "id" "text" --includeSnapshot true # Fill an element and return a snapshot
brave-devtools handle_dialog 1 accept # Handle a browser dialog (accept/dismiss)
brave-devtools handle_dialog 1 dismiss --promptText "hi" # Dismiss a dialog with prompt text
brave-devtools hover 1 "id" # Hover over the provided element
brave-devtools hover 1 "id" --includeSnapshot true # Hover over an element and return a snapshot
brave-devtools press_key 1 "Enter" # Press a key or key combination ("Control+A", "Escape")
brave-devtools press_key 1 "Control+A" --includeSnapshot true # Press a key and return a snapshot
brave-devtools type_text 1 "hello" # Type text using keyboard into a focused input
brave-devtools type_text 1 "hello" --submitKey "Enter" # Type text and press a submit key
brave-devtools upload_file 1 "id" "file.txt" # Upload a file through a provided element
brave-devtools upload_file 1 "id" "file.txt" --includeSnapshot true # Upload a file and return a snapshot
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 193 lines · 32 tokens per session scan A 15bd216a387d
brave-devtools-cli is a skill published in the GitHub repository triuzzi/brave-devtools-mcp (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,824 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to chrome-devtools-cli, differing in 200 lines, and is treated as a copy.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
cookie-debugging
Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party…
chrome-devtools
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).
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
webview-devtools
Use webview-devtools-mcp to inspect and automate an already-instrumented WebView/page: choose this skill when the user’s target environment is configured so the page injects wdmcp’s target.js (or the user is explicitly asking to work with such a configured WebView). If the page is not yet injecting target.js, do not…
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.