A Model Context Protocol (MCP) server for RAD Security, providing AI-powered security insights for Kubernetes and cloud environments.

npm install @rad-security/mcp-server

• Node.js 20.x or higher

The following environment are required required to use the MCP server with Rad Security:

RAD_SECURITY_ACCESS_KEY_ID="your_access_key"
RAD_SECURITY_SECRET_KEY="your_secret_key"
RAD_SECURITY_ACCOUNT_ID="your_account_id"

You can control which toolkits are exposed by the MCP server using these environment variables:

• INCLUDE_TOOLKITS: Comma-separated list of toolkits to include (only these will be enabled)
• EXCLUDE_TOOLKITS: Comma-separated list of toolkits to exclude (all except these will be enabled)

Available toolkits:

• containers - Container inventory operations
• clusters - Kubernetes cluster operations
• identities - Identity management operations
• audit - Audit log operations
• cloud_inventory - Cloud resource inventory
• images - Container image operations
• kubeobject - Kubernetes resource operations
• misconfigs - Misconfiguration detection
• runtime - Runtime analysis operations
• runtime_network - Network traffic analysis
• threats - Threat vector operations
• findings - Security findings operations
• cves - CVE database operations
• inbox - Inbox item operations
• workflows - Workflow execution operations

Examples:

# Only enable workflow toolkit
INCLUDE_TOOLKITS="workflows"

# Enable only containers and images toolkits
INCLUDE_TOOLKITS="containers,images"

# Exclude workflow toolkit (enable all others)
EXCLUDE_TOOLKITS="workflows"

# Exclude runtime and threat toolkits
EXCLUDE_TOOLKITS="runtime,threats"

Note: If INCLUDE_TOOLKITS is set, EXCLUDE_TOOLKITS is ignored.

You can also use few operations without authentication:

• List CVEs
• Get details of a specific CVE
• Get latest 30 CVEs
• List Kubernetes resource misconfiguration policies

It's quite problematic to set ENV variables in cursor IDE.

So, you can use the following start.sh script to start the server.

./start.sh

Please set the ENV variables in the start.sh script first!

You can use the following config to start the server in Claude Desktop.

{
  "mcpServers": {
    "rad-security": {
      "command": "npx",
      "args": ["-y", "@rad-security/mcp-server"],
      "env": {
        "RAD_SECURITY_ACCESS_KEY_ID": "<your-access-key-id>",
        "RAD_SECURITY_SECRET_KEY": "<your-secret-key>",
        "RAD_SECURITY_ACCOUNT_ID": "<your-account-id>"
      }
    }
  }
}

To filter toolkits, add INCLUDE_TOOLKITS or EXCLUDE_TOOLKITS to the env:

{
  "mcpServers": {
    "rad-security": {
      "command": "npx",
      "args": ["-y", "@rad-security/mcp-server"],
      "env": {
        "RAD_SECURITY_ACCESS_KEY_ID": "<your-access-key-id>",
        "RAD_SECURITY_SECRET_KEY": "<your-secret-key>",
        "RAD_SECURITY_ACCOUNT_ID": "<your-account-id>",
        "EXCLUDE_TOOLKITS": "workflows"
      }
    }
  }

docker build -t rad-security/mcp-server .
docker run \
  -e TRANSPORT_TYPE=streamable \
  -e RAD_SECURITY_ACCESS_KEY_ID=your_access_key \
  -e RAD_SECURITY_SECRET_KEY=your_secret_key \
  -e RAD_SECURITY_ACCOUNT_ID=your_account_id \
  -p 3000:3000 \
  rad-security/mcp-server

With toolkit filters:

docker run \
  -e TRANSPORT_TYPE=streamable \
  -e RAD_SECURITY_ACCESS_KEY_ID=your_access_key \
  -e RAD_SECURITY_SECRET_KEY=your_secret_key \
  -e RAD_SECURITY_ACCOUNT_ID=your_account_id \
  -e INCLUDE_TOOLKITS=workflows,containers \
  -p 3000:3000 \
  rad-security/mcp-server

Note: The SSE transport is now deprecated in favor of Streamable HTTP. It's still supported for backward compatibility, but it's recommended to use Streamable HTTP instead.

docker build -t rad-security/mcp-server .
docker run \
  -e TRANSPORT_TYPE=sse \
  -e RAD_SECURITY_ACCESS_KEY_ID=your_access_key \
  -e RAD_SECURITY_SECRET_KEY=your_secret_key \
  -e RAD_SECURITY_ACCOUNT_ID=your_account_id \
  -p 3000:3000 \
  rad-security/mcp-server

• Account Inventory

  • List clusters and their details*

• Containers Inventory

  • List containers and their details*

• Security Findings

  • List and analyze security findings*

• Runtime Security

  • Get process trees of running containers*
  • Get runtime baselines of running containers*
  • Analyze process behavior of running containers*

• Network Security

  • Monitor HTTP requests*
  • Track network connections*
  • Analyze network patterns*

• Identity and Access

  • List identities*
  • Get identity details*

• Audit

  • List who shelled into a pod*

• Cloud Security

  • List and monitor cloud resources*
  • Get resource details and compliance status*

• Images

  • Get SBOMs*
  • List images and their vulnerabilities*
  • Get top vulnerable images*

• Kubernetes Objects

  • Get details of a specific Kubernetes resource*
  • List Kubernetes resources*
  • List Kubernetes resource misconfiguration policies*

• Threat Vector

  • List threat vectors*
  • Get details of a specific threat vector*

• CVEs

  • List CVEs
  • Get details of a specific CVE
  • Get latest 30 CVEs

* - requires authentication and account in Rad Security.

# Install dependencies
npm install

# Run type checking
npm run type-check

# Run linter
npm run lint

# Build
npm run build

MIT License - see the LICENSE file for details