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/babelwrap/babelwrap-mcp-js/babelwrap-mcpgit clone --depth 1 https://github.com/babelwrap/babelwrap-mcp-jsWrote 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/babelwrap/babelwrap-mcp-js/babelwrap-mcp)<a href="https://agentmods.dev/mcp/babelwrap/babelwrap-mcp-js/babelwrap-mcp"><img src="https://agentmods.dev/badge/mcp/babelwrap/babelwrap-mcp-js/babelwrap-mcp.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
babelwrap-mcp 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 5d 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
{ "babelwrap-mcp": { "command": "npx", "args": [ "-y", "babelwrap-mcp" ] } }
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.
- 5d ago First seen · 9 lines scan A df62410d2b80
babelwrap-mcp is an MCP server published in the GitHub repository babelwrap/babelwrap-mcp-js (0 stars, last pushed 5mo 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
unbrowser
Web access for LLM agents. One static binary. No Chrome. Runs locally from the pyunbrowser Python package.
feedthrough
Debug bridge inside your web app: an agent reads the DOM, console and network. Any browser. Runs locally from the @feedthrough/mcp npm package. Needs 2 environment variables to run.
invisible-playwright-mcp
Stealth Firefox browser as an MCP server for AI agents. Runs locally from the invisible-playwright-mcp Python package.
trusty-squire
Trusty Squire signs up / in to websites for you so you don’t have to. Runs locally from the @trusty-squire/mcp npm package.
browser-for-ai
CDP-native MCP server that lets an AI agent drive Chrome at full depth — deep network/console read, robust interaction, multi-session, and API-flow → runnable-code extraction. Runs locally from the browser-for-ai npm package.
helmdeck
Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent. Runs locally from the @helmdeck/mcp-bridge npm package. Needs 2 environment variables to run.