# io.github.MCPShield-Dev/mcpshield

> Use this tool when you need to detect and prevent security threats on MCP servers, such as tool poisoning and injection attacks. It scans for potential vulnerabilities and provides output on detected threats, allowing for prompt action to secure the server. Ideal for server administrators seeking to protect their MCP environments from malicious activities.

Canonical page: https://skillsregistry.net/skills/io-github-mcpshield-dev-mcpshield  
JSON: https://api.skillsregistry.net/v1/skills/io-github-mcpshield-dev-mcpshield

## Description

Security scanner for MCP servers - detects tool poisoning and injection

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 2.0.2
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.MCPShield-Dev%2Fmcpshield)
- **Repository:** <https://github.com/MCPShield-Dev/mcpshield>

## 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": "io-github-mcpshield-dev-mcpshield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-mcpshield-dev-mcpshield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-mcpshield-dev-mcpshield/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