1. Conduid
  2. Security
  3. AgentDefense Bench
MCP server · Security

AgentDefense Bench

by · github.com/arunsanna/AgentDefense-Bench

A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems

Unclaimed last commit 6 months ago ai-securitybenchmarkdatasetjailbreakingllmmcpprompt-injection
InstallView source
23Low

Scored 10 hours ago · breakdown

About AgentDefense Bench

AgentDefense Bench is an MCP server published by arunsanna in the Security category: a comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems.

The repository has 15 stars and 5 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/arunsanna/AgentDefense-Bench

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about AgentDefense Bench

Powered by Claude

Ask about AgentDefense Bench — answers draw on its README.

Security checks

6 checks have not been run yet.

Questions

About AgentDefense Bench

How do I install AgentDefense Bench?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is AgentDefense Bench safe to use with an AI agent?

Its trust score is 23 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is AgentDefense Bench still maintained?

The last commit was 6 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.