1. Conduid
  2. Data
  3. Guardbench
MCP server · Data

Guardbench

A guard-agnostic benchmark for MCP injection / exfil / tool-poisoning detection. Versioned cases + a language-agnostic runner that scores any guard through its own published CLI.

34Low

Scored 11 days ago · breakdown

About Guardbench

Guardbench is an MCP server in the Data category: a guard-agnostic benchmark for MCP injection / exfil / tool-poisoning detection. Versioned cases + a language-agnostic runner that scores any guard through its own published CLI. It has been installed 0 times through Conduid.

Install

Clone
git clone https://github.com/getmcpm/mcp-guardbench

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 Guardbench

Powered by Claude · Grounded in docs

I know everything about Guardbench. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • ·Scoped permissionsNot checked yet.
Questions

About Guardbench

How do I install Guardbench?

Run git clone https://github.com/getmcpm/mcp-guardbench, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Guardbench safe to use with an AI agent?

Its trust score is 34 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 Guardbench still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.