# MCPSecBench

> MCPSecBench — ais2lab-mcpsecbench. Use this tool when you need to systematically evaluate and test the security of model context protocols, providing a comprehensive benchmark and playground for identifying vulnerabilities and weaknesses. It solves problems related to protocol security testing, validation, and optimization, accepting model context protocols as input and producing detailed security assessment reports as output. Ideal for use cases involving protocol development, testing, and hardening, MCPSecBench streamlines the security evaluation process.

Canonical page: https://skillsregistry.net/skills/ais2lab-mcpsecbench  
JSON: https://api.skillsregistry.net/v1/skills/ais2lab-mcpsecbench

## Description

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/AIS2Lab/MCPSecBench)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ais2lab-mcpsecbench"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ais2lab-mcpsecbench` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ais2lab-mcpsecbench/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt