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/AIS2Lab/MCPSecBenchWrote 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/ais2lab/mcpsecbench/malicious)<a href="https://agentmods.dev/mcp/ais2lab/mcpsecbench/malicious"><img src="https://agentmods.dev/badge/mcp/ais2lab/mcpsecbench/malicious/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/ais2lab/mcpsecbench/malicious"><img src="https://agentmods.dev/badge/mcp/ais2lab/mcpsecbench/malicious.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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
{
"malicious": {
"command": "uv",
"args": [
"--directory",
"/usr/games/mcp/MCPSecCode/mcpbench",
"run",
"maliciousadd.py"
]
}
}What else claude_desktop_config.json configures
This page is one entry in a file that holds 4. 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.
- 1mo ago First seen · 11 lines scan A e656903a5d8c
malicious is an MCP server published in the GitHub repository AIS2Lab/MCPSecBench (40 stars, last pushed 7mo 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.
Other mcp servers, from other repositories
cloudwatch-appsignals
MCP server "cloudwatch-appsignals" as configured in awslabs/mcp. Runs locally from the awslabs.cloudwatch-applicationsignals-mcp-server@latest Python package. Needs 1 environment variable to run.
cloudwatch
MCP server "cloudwatch" as configured in awslabs/mcp. Runs locally from the awslabs.cloudwatch-mcp-server@latest Python package. Needs 1 environment variable to run.
awesome-copilot
MCP server "awesome-copilot" as configured in microsoft/mcp-dotnet-samples. Runs in Docker (ghcr.io/microsoft/mcp-dotnet-samples/awesome-copilot:1.0.2026092200).
strata
MCP server for progressive tool usage at any scale (see https://klavis.ai). Remote server at strata.klavis.ai.
stockbit-mcp
Indonesian exchange (IDX) via your own Stockbit account: quotes, bandarmology, charts. Unofficial. Runs locally from the stockbit-mcp npm package. Needs 4 environment variables to run.
rollbar
MCP server "rollbar" as configured in rollbar/rollbar-mcp-server. Runs /rollbar-mcp-server/build/index.js with node. Needs 1 environment variable to run.