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.
git clone --depth 1 https://github.com/vmihalis/hacker-bobWrote 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/vmihalis/hacker-bob/hacker-bob-brutalist)<a href="https://agentmods.dev/mcp/vmihalis/hacker-bob/hacker-bob-brutalist"><img src="https://agentmods.dev/badge/mcp/vmihalis/hacker-bob/hacker-bob-brutalist.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
brutalist 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 8d 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
{
"brutalist": {
"command": "npx",
"args": [
"-y",
"@brutalist/[email protected]"
]
}
}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.
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.
- 8d ago First seen · 9 lines scan A 00b404da44fb
brutalist is an MCP server published in the GitHub repository vmihalis/hacker-bob (97 stars, last pushed 9d ago), licensed Apache-2.0. 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
sabba
SABBA: a security templates CLI and MCP server for coding agents that prove findings by running them. Runs locally from the sabba Python package.
code-reviewer-ai-mcp
Code Reviewer Ai MCP server. Tools: review code, check security, suggest improvements. Built by MEOK AI Labs. Runs locally from the code-reviewer-ai-mcp Python package.
crs-mcp
MCP server "crs-mcp" as configured in nickharris808/crs-mcp. Runs locally from the crs-mcp Python package.
gitlab-mcp
MCP server (stdio) — proxy fino sobre a REST API v4 de um GitLab CE self-hosted, focado em navegar MRs e deixar review inline. Runs locally from the @vinihcrosa/gitlab-mcp npm package.
mcp-devils-advocate
MCP server "mcp-devils-advocate" as configured in AleBrito124356/mcp-devils-advocate. Runs locally from the mcp-devils-advocate Python package. Needs 1 environment variable to run.
offsec
MCP server that gives AI agents authorized-only offensive-security tools: recon, CVE intel, JS analysis, port scanning. Runs locally from the offsec-mcp Python package. Needs 2 environment variables to run.