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/browserbase/stagehand/claude-code-stagehandgit clone --depth 1 https://github.com/browserbase/stagehandGrade A, and why
stagehand 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 yesterday.
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
{
"stagehand": {
"command": "node",
"args": [
"../core/dist/facade/stdio-server.mjs"
]
}
}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.
- yesterday First seen · 8 lines scan A 9e8cfefea3f0
stagehand is an MCP server published in the GitHub repository browserbase/stagehand (24,098 stars, last pushed yesterday), 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 2026-08-30.
Other mcp servers, from other repositories
fortress
Open stealth-browser framework — drive a real recompiled-Chromium (Fortress) that defeats bot-detection fingerprint suites. Drop-in stealth for browser-use, Playwright, Crawl4AI, with an MCP server for AI agents. Runs locally from the tilion Python package. Needs 5 environment variables to run.
air-sdk
Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction. Runs locally from the @arcede/air-sdk npm package. Needs 1 environment variable to run.
shipcheck
MCP server "shipcheck", hosted remotely at realtor-all-enclosed-altered.trycloudflare.com, as configured in wtaylorwilson/shipcheck-preview-qa.
playwright-test
A high-level API to automate web browsers. Runs locally from the playwright npm package.
context7
MCP server "context7" as configured in evan043/claude-cli-advanced-starter-pack. Launched with cmd /c npx -y @upstash/context7-mcp.
site-intel
MCP server "site-intel" as configured in evan043/claude-cli-advanced-starter-pack. Runs src/site-intel/mcp-server.js with node.