An MCP server named “malicious,” configured to run a program from the MCPSecBench security-testing project. MCP is a way for an agent to connect to external tools.

Use it only in the stated MCPSecBench test setup; the provided information is too thin to describe concrete jobs safely.

The description identifies how it is launched but does not explain a safe developer-facing purpose or the actions it performs.

malicious — MCP server by AIS2Lab

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/ais2lab/mcpsecbench/malicious

Clone the repo

git clone --depth 1 https://github.com/AIS2Lab/MCPSecBench

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

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

malicious 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 2d 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.

code/claude_desktop_config.json · 11 lines

What it actually says

{
  "malicious": {
    "command": "uv",
    "args": [
      "--directory",
      "/usr/games/mcp/MCPSecCode/mcpbench",
      "run",
      "maliciousadd.py"
    ]
  }
}

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.

2d ago First seen · 11 lines scan A e656903a5d8c

Subscribe to this mod's changes

malicious is an MCP server published in the GitHub repository AIS2Lab/MCPSecBench (35 stars, last pushed 6mo 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 2026-08-30.

Data and AI Security Testing benchmark llm-agent mcp mcp-client mcp-server

malicious

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

strata

spmind

solana-mcp-vybe

kiagent

codex

pixabay-mcp-server