Hosted MCP server · #125 most used on Smithery

SkillAudit

megamind-0x/skillaudit

Security scanner for AI agent skills and MCP servers. Detects credential theft, data exfiltration, prompt injection, obfuscated code, and 80+ threat patterns. Free API + CLI (npx skillaudit). Premium deep scans via x402 micropayments.

Backend & APIs Data & databases Security

Install ↓Smithery ↗Website ↗

Uses: 4.3k
Tools: 4
Runs: Hosted
Listed: 9mo ago

Get started

Add it to your agent

npx -y @smithery/cli@latest install megamind-0x/skillaudit --client claude

Swap --client claude for cursor, vscode, windsurf or another client. The CLI asks for any required settings.

claude mcp add --transport http skillaudit https://server.smithery.ai/megamind-0x/skillaudit/mcp

A hosted server: nothing to install. Run /mcp in Claude Code to sign in if it asks.

[mcp_servers.skillaudit]
url = "https://server.smithery.ai/megamind-0x/skillaudit/mcp"

Add to ~/.codex/config.toml.

{
  "mcpServers": {
    "skillaudit": {
      "url": "https://server.smithery.ai/megamind-0x/skillaudit/mcp"
    }
  }
}

Add to ~/.cursor/mcp.json.

{
  "servers": {
    "skillaudit": {
      "type": "http",
      "url": "https://server.smithery.ai/megamind-0x/skillaudit/mcp"
    }
  }
}

Add to .vscode/mcp.json.

gemini mcp add --transport http skillaudit https://server.smithery.ai/megamind-0x/skillaudit/mcp

Saved to .gemini/settings.json.

What it can do

4 tools

scan_url1 paramScan a skill/MCP server by URL for security issues. Returns risk level, findings, and verdict.

Parameter	Type	Description
`url`	string	URL of the skill file or MCP server to scan

scan_github2 paramsScan a GitHub repository for skill files and security issues.

Parameter	Type	Description
`repo`	string	GitHub repository in owner/name format (e.g. modelcontextprotocol/servers)
`branch`	string	Branch to scan (default: main)

gate_check2 paramsPre-install gate check. Returns allow/warn/deny decision for a skill URL.

Parameter	Type	Description
`url`	string	URL of the skill to check
`threshold`	string	Risk threshold (default: moderate). Deny if risk >= threshold.

reputation_check1 paramCheck the reputation of a domain based on aggregated scan history.

Parameter	Type	Description
`domain`	string	Domain to check (e.g. example.com)