Model Context Protocol (MCP) for AI Security

GridinSoft Inspector provides a native implementation of the Model Context Protocol (MCP), enabling seamless integration between our threat intelligence services and AI models (such as Claude, GPT-4, or local LLMs). This interface allows your AI assistants to perform real-time security assessments, domain reputation checks, and URL scanning directly within your workflow.

Model Context Protocol (MCP) Setup

The Model Context Protocol (MCP) allows your AI tools (like Claude Desktop) to connect directly to GridinSoft Inspector services. This enables real-time domain analysis and URL scanning within your AI chat interface.

BASE URL https://inspector.gridinsoft.com/mcp/v1

Prerequisites

You must have a GridinSoft Inspector account.
An MCP-compatible client (e.g., Claude Desktop).
Node.js (for using @modelcontextprotocol/server-http).

Claude Desktop Configuration

To integrate GridinSoft tools into Claude Desktop, follow these steps:

Open your Claude Desktop configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add gridinsoft to your mcpServers list:

{
  "mcpServers": {
    "gridinsoft": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-http",
        "--url",
        "https://inspector.gridinsoft.com/mcp/v1",
        "--header",
        "Authorization: Bearer YOUR_PRIVATE_APIKEY"
      ]
    }
  }
}

Authentication

Authentication is handled via a Bearer token in the Authorization header. Your API key serves as the token.

Header	Value
Authorization	Bearer YOUR_PRIVATE_APIKEY

Tip: If you use multiple MCP servers, ensure they are all listed under the mcpServers key in your configuration.

MCP Tool Examples

GridinSoft MCP server provides several tools that AI assistants can use to help with security tasks. below are the details and example payloads for each tool.

1. inspect_domain

Retrieves detailed information about a domain, including its security category and threat level.

Argument	Type	Required	Description
domain	String	Yes	The domain name to analyze (e.g., "example.com").

Example Input:

{
  "name": "inspect_domain",
  "arguments": {
    "domain": "google.com"
  }
}

Example Output (Success):

{
  "content": [
    {
      "type": "text",
      "text": "{\"domain\":\"google.com\",\"category\":\"Clean\",\"status\":\"safe\"}"
    }
  ]
}

2. scan_url

Scans a specific URL for redirects, phishing, and malware signatures.

Argument	Type	Required	Description
url	String	Yes	The full URL to scan (e.g., "http://suspicious.site/page").

Example Input:

{
  "name": "scan_url",
  "arguments": {
    "url": "https://gridinsoft.com"
  }
}

3. get_balance

Returns the current credit balance and subscription plan details for the authenticated user.

This tool requires no arguments.

Example Input:

{
  "name": "get_balance",
  "arguments": {}
}

Example Output:

{
  "content": [
    {
      "type": "text",
      "text": "{\"credits\":500,\"plan\":\"Enterprise\",\"subscription_end_date\":\"2026-12-31\"}"
    }
  ]
}

MCP Usage Statistics

Monitor your MCP tool execution and credit consumption below. Statistics are updated in real-time as your AI assistant interacts with the GridinSoft MCP server.

Detailed per-tool execution logs are coming soon to this dashboard. Currently, you can view your overall credit balance in your Profile or by using the get_balance MCP tool.

Current Limits

Tool Name	Daily Limit	Cost per Execution
inspect_domain	Unlimited (per credits)	1 credit
scan_url	Unlimited (per credits)	3 credits
get_balance	Free	0 credits

Ready to get started?