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 mcp/lunaparker/waveapps-mcp/brave-devtoolsgit clone --depth 1 https://github.com/LunaParker/waveapps-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/lunaparker/waveapps-mcp/brave-devtools)<a href="https://agentmods.dev/mcp/lunaparker/waveapps-mcp/brave-devtools"><img src="https://agentmods.dev/badge/mcp/lunaparker/waveapps-mcp/brave-devtools.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
brave-devtools 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 4d 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.
What it actually says
{
"brave-devtools": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp-for-brave@latest",
"--isolated"
],
"env": {}
}
}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.
- 4d ago First seen · 12 lines scan A 2bc5ca1b2188
brave-devtools is an MCP server published in the GitHub repository LunaParker/waveapps-mcp (2 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
browser-use
Make websites accessible for AI agents. Runs locally from the browser-use Python package.
chainlink-safe-fetch
MCP server "chainlink-safe-fetch" as configured in dollspace-gay/chainlink. Runs .claude/mcp/safe-fetch-server.py with python.
devharness
MCP server that connects AI assistants to Chrome DevTools Protocol for runtime debugging - set breakpoints, inspect variables, monitor network traffic, and automate browser interactions. Runs locally from the devharness npm package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
crawlforge-mcp-server
Web scraping, crawling, deep research & autonomous extraction — 29 MCP tools, clean Markdown/JSON. Runs locally from the crawlforge-mcp-server npm package. Needs 3 environment variables to run.
browser-cognition-mcp
Brocogni -- Making Playwright make sense to AI agents. MCP server for semantic browser observation and self-healing selectors. Runs locally from the browser-cognition-mcp npm package.