MCP Guardrail is an AI-powered security layer that aggregates multiple MCP servers into a single protected interface with intelligent content moderation. It prevents prompt injection attacks and malicious content by scanning all interactions through the General Analysis moderation API, acting as a transparent proxy between MCP clients (Cursor, Claude Desktop, Claude Code) and backend servers. Key features: - **AI-powered content moderation** to detect and block prompt injection attacks, malicious inputs, and inappropriate content using the General Analysis API. - **Multi-server aggregation** combining local (stdio) and remote (HTTP/SSE) MCP servers with automatic tool name prefixing to prevent conflicts. - **Zero-configuration setup** via CLI tool that automatically detects and updates MCP config files for Cursor, Claude Desktop, and Claude Code. - **Transparent proxying** that seamlessly manages tools, prompts, and resources between clients and aggregated backend servers without code changes. - **Zero-install deployment** via npx without local installation requirements, or standalone usage with environment variable configuration.

MCP Guardrail

An MCP (Model Context Protocol) guardrail with built-in AI-powered moderation that aggregates multiple MCP servers into one secure interface.

Overview

The MCP Guardrail provides AI-powered security and easy configuration for your MCP (Model Context Protocol) setup. It automatically detects your existing MCP configuration files and adds a protective layer with intelligent moderation capabilities.

Key features:

Quick Start

The easiest way to get started is using the General Analysis CLI tool:

# Install the CLI tool
pip3 install generalanalysis==0.1.7
Login to your account
ga login
Configure MCP settings for Cursor, Claude Desktop, and Claude Code
ga configure

This will automatically update your MCP configuration files with the guardrail setup.

How It Works

graph LR
    A[MCP Client] --> B[MCP Guard]
    B --> C[MCP Server]
    C --> D[Tool Output]
    D --> B
    B --> E{GA Guardrail}
    E -->|Safe| A
    E -->|Blocked| F[Alert]

Usage

Direct Usage with npx

No installation required! Use directly in your Cursor or Claude Desktop MCP configuration:

{
  "mcpServers": {
    "protected_server": {
      "command": "npx",
      "args": [
        "-y",
        "@general-analysis/mcp-guard",
        "[{\"name\":\"server1\",\"command\":\"path/to/server\",\"args\":[\"arg1\"]}]"
      ]
    }
  }
}

Standalone Usage

npx -y @general-analysis/mcp-guard '[{"name":"server1","command":"path/to/server","args":["arg1"]}]'

Configuration

#### Local Servers (Stdio)

For local MCP servers that communicate via stdio:

{
  "mcpServers": {
    "protected_server": {
      "command": "npx",
      "args": [
        "-y",
        "@general-analysis/mcp-guard",
        "[{\"name\":\"my-local-server\",\"command\":\"node\",\"args\":[\"path/to/server.js\"]}]"
      ],
      "env": {
        "API_KEY": "your-general-analysis-api-key",
        "ENABLE_GUARD_API": "true"
      }
    }
  }
}

#### Remote Servers (HTTP/SSE)

For remote MCP servers accessible via HTTP or Server-Sent Events:

{
  "mcpServers": {
    "protected_server": {
      "command": "npx",
      "args": [
        "-y",
        "@general-analysis/mcp-guard",
        "[{\"name\":\"my-remote-server\",\"url\":\"https://api.example.com/mcp\"}]"
      ],
      "env": {
        "API_KEY": "your-general-analysis-api-key",
        "ENABLE_GUARD_API": "true"
      }
    }
  }
}

Environment Variables

Complete Example for Cursor/Claude Desktop

Add this to your MCP configuration file:

{
  "mcpServers": {
    "guardrail": {
      "command": "npx",
      "args": [
        "-y",
        "@general-analysis/mcp-guard",
        "[{\"name\":\"local-filesystem\",\"command\":\"npx\",\"args\":[\"@modelcontextprotocol/server-filesystem\",\"/path/to/files\"]},{\"name\":\"remote-api\",\"url\":\"https://api.example.com/mcp\"}]"
      ],
      "env": {
        "API_KEY": "your-general-analysis-api-key",
        "ENABLE_GUARD_API": "true"
      }
    }
  }
}

Standalone Command Line Example

# Set environment variables
export API_KEY="your-general-analysis-api-key"
export ENABLE_GUARD_API="true"
Run with mixed local and remote servers
npx -y @general-analysis/mcp-guard '[
  {
    "name": "local-filesystem",
    "command": "npx",
    "args": ["@modelcontextprotocol/server-filesystem", "/path/to/files"]
  },
  {
    "name": "remote-api",
    "url": "https://api.example.com/mcp"
  }
]'

Requirements

License

MIT