# mcpsec

> mcpsec — manthanghasadiya-mcpsec. Use this tool when you need to identify vulnerabilities in the Model Context Protocol (MCP) by dynamically fuzzing the protocol to discover state violations, transport crashes, and application-layer logic flaws. It takes protocol implementations as input and outputs potential exploitability reports, helping you secure your systems before AI agents can exploit them. Ideal for use in security testing and protocol development contexts.

Canonical page: https://skillsregistry.net/skills/manthanghasadiya-mcpsec  
JSON: https://api.skillsregistry.net/v1/skills/manthanghasadiya-mcpsec

## Description

An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** cloud-infra
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/manthanghasadiya/mcpsec)

## 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": "manthanghasadiya-mcpsec"
    }
  }
}
```

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