io.github.dl-eigenart/agentshield-mcp

io.github.dl-eigenart/agentshield-mcp·v0.1.3·AI & LLMs

Quality Score

/100

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

Repository →

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agentshield-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@eigenart/agentshield-mcp"
      ],
      "env": {
        "AGENTSHIELD_API_KEY": "<your-agentshield_api_key>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "agentshield-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@eigenart/agentshield-mcp"
      ],
      "env": {
        "AGENTSHIELD_API_KEY": "<your-agentshield_api_key>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)