home / mcp / aim guard mcp server

AIM Guard MCP Server

AIM MCP Server :: Guard and Protect your MCPs & AI Chatting

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "aim-intelligence-aim-mcp": {
      "command": "npx",
      "args": [
        "aim-guard-mcp"
      ]
    }
  }
}

AIM Guard MCP is an MCP server that provides AI-powered security analysis, safety instructions, and threat detection for interactions between AI agents and various MCPs. It helps you harden interactions, scan for sensitive data, and validate URLs and prompts before actions are taken by your agents.

How to use

You run AIM Guard MCP as an MCP server that your MCP client can talk to through a standard stdio endpoint. Add it to your client's server configuration, then invoke the available tools to analyze content, strengthen prompts, detect prompt injections, and scan for credentials or unsafe links before your agents proceed with actions.

How to install

Prerequisites: ensure you have Node.js and npm installed on your system before starting. You will install the MCP server client and run it locally or through a package manager.

npm install -g aim-guard-mcp
aim-guard-mcp

Alternative: install AIM MCP via Smithery if you are integrating with a Claude Desktop workflow.

npx -y @smithery/cli install @AIM-Intelligence/aim-mcp --client claude

Another common approach is to run the MCP server via NPX directly, which is the recommended quick-start path.

npx aim-guard-mcp

If you want to run a local stdio MCP configuration in your client, you can reference this example configuration.

{
  "servers": {
    "aim-guard": {
      "type": "stdio",
      "command": "npx",
      "args": ["aim-guard-mcp"]
    }
  }
}

Additional setup notes

You can also install and run AIM Guard MCP in a development or CI environment using the standard npm-based workflow and ensure the command is available in your PATH.

Available tools

ai-safety-guard

Provides contextual security instructions and precautions for AI agents before they interact with other MCPs, with operation-specific warnings and red flags.

aim-text-guard

Analyzes text content for harmful or inappropriate content using AIM Intelligence API, returning detailed JSON results.

aim-security-prompt-tool

Enhances user prompts with security instructions to promote safer AI interactions, with multi-level security enhancements.

prompt-injection-detector

Detects prompt injection attempts based on OWASP LLM01:2025 patterns, assigns risk scores, and provides threat reporting.

credential-scanner

Scans text for exposed credentials (API keys, tokens, passwords, etc.), masks findings, and provides security recommendations.

url-security-validator

Validates URL safety, detects phishing/harmful domains, and checks HTTPS enforcement.