LLM Redteam runs on your own machine — the client starts it, so there is no endpoint to ping. 379 installs a week from npm. Last commit 6 Nov 2026.
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
What the code does
We read the source, 1 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
…mendation: "A server-supplied authorization URL interpolated into a shell command is command injection: a URL with `\"; rm -rf ~` or `&calc` runs on the user's machine (MCP spec: OAuth authorization URL validation). Validate the URL (https only) and open it without a shell: the `…
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const read = (f: string) => JSON.parse(fs.readFileSync(path.join(dir, f), "utf8"));
version = execFileSync(path.join(path.dirname(bin), "pip"), ["show", "cisco-ai-mcp-scanner"], { encoding: "utf8" }).match(/^Version: (.+)$/m)?.[1] ?? version;
pattern: /\b(?:read|cat|include|attach|append)\b[^.]{0,80}(?:\.ssh\b|\bid_rsa\b|\.env\b|\.aws[\\/]credentials\b|\bprivate[\s_-]?key\b|\.npmrc\b|\.cursor[\\/]mcp\.json\b|\bclaude_desktop_config\.json\b|\.kube[\\/]config\b)/i,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch LLM Redteam and you get told the day something new turns up.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add llm-redteam -- npx -y @guardbee/mcp-llm-redteam{
"mcpServers": {
"llm-redteam": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-llm-redteam"
]
}
}
}[mcp_servers.llm-redteam]
command = "npx"
args = ["-y", "@guardbee/mcp-llm-redteam"]{
"mcpServers": {
"llm-redteam": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-llm-redteam"
]
}
}
}{
"servers": {
"llm-redteam": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-llm-redteam"
]
}
}
}Alternatives to LLM Redteam
same job, measured the same wayActive jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Kiwoom Securities REST API for Korean markets — 236 endpoints, streaming, gated order execution
Premium agentic endpoint for dan-jailbreak-filter-mcp.
LLM-assisted biomedical literature screening and extraction for PubMed, GEO, and preprints.
Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.
Email for AI agents. Create mailboxes, send/receive emails, and auto-extract verification codes.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
LLM Redteam — questions
Answers built from our own checks of this server.