Skip to content
appsgit

Agent Security Scanner MCP

Agent Security Scanner MCP is an MCP server that adds developer tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. It has 122 GitHub stars, is released under the MIT license and runs locally with npx -y agent-security-scanner-mcp.

github.com/sinewaveai/agent-security-scanner-mcp (opens in a new tab)

View on GitHub (opens in a new tab)

Install Agent Security Scanner MCP

Generated from the server's MCP registry entry. Replace your-value with your own values.

Claude Desktop

claude_desktop_config.json
{
  "mcpServers": {
    "agent-security-scanner-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-security-scanner-mcp"
      ]
    }
  }
}

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

Claude Code

claude mcp add --transport stdio agent-security-scanner-mcp -- npx -y agent-security-scanner-mcp

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "agent-security-scanner-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-security-scanner-mcp"
      ]
    }
  }
}

Project file; use ~/.cursor/mcp.json to enable it in every project.

VS Code

.vscode/mcp.json
{
  "servers": {
    "agent-security-scanner-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-security-scanner-mcp"
      ]
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

About Agent Security Scanner MCP

Security scanner for AI coding agents, MCP servers, prompts, and AI-suggested packages. Run it before Claude Code, Cursor, Windsurf, Cline, OpenCode, or another agent trusts new code, tools, prompts, or dependencies.

  • ai-security
  • claude-code
  • cursor
  • hallucination-detection
  • mcp
  • mcp-server
  • prompt-injection
  • sast
  • security
  • vulnerability-scanner

Similar MCP servers

More developer tools MCP servers

All Developer tools

FAQ

Agent Security Scanner MCP FAQ

Still curious? Email info@appsgit.com.

What is Agent Security Scanner MCP?

Agent Security Scanner MCP is an MCP server that adds developer tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. It has 122 GitHub stars, is released under the MIT license and runs locally with npx -y agent-security-scanner-mcp. The source code is at github.com/sinewaveai/agent-security-scanner-mcp.

How do I install the Agent Security Scanner MCP MCP server?

Add the command npx -y agent-security-scanner-mcp to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.

Is Agent Security Scanner MCP free?

The server is open source under the MIT license, so running it is free. It does not declare any required API key.

Is Agent Security Scanner MCP actively maintained?

The most recent commit was on Sep 2, 2026. The latest release is v4.4.5, published Jun 22, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.