AIM Guard
STDIOAI-powered security server providing safety analysis and protection for AI agents using MCPs.
AI-powered security server providing safety analysis and protection for AI agents using MCPs.
🛡️ AIM MCP Server :: Guard and Protect your MCPs & AI Agents
A Model Context Protocol (MCP) server that provides AI-powered security analysis and safety instruction tools. This server helps protect AI agents by providing security guidelines, content analysis, and cautionary instructions when interacting with various MCPs and external services.
To install aim-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @AIM-Intelligence/aim-mcp --client claude
npx aim-guard-mcp
npm install -g aim-guard-mcp aim-guard-mcp
npm install aim-guard-mcp
Add to your MCP client configuration:
{ "servers": { "aim-guard": { "type": "stdio", "command": "npx", "args": ["aim-guard-mcp"] } } }
# Get safety instructions for database operations { "name": "ai-safety-guard", "arguments": { "mcp_type": "database", "operation_type": "query", "sensitivity_level": "confidential" } }
# This will analyze the text for harmful content { "name": "aim-text-guard", "arguments": { "text": "This is a sample text to analyze for safety." } }
# Enhance a user prompt with security instructions { "name": "aim-security-prompt-tool", "arguments": { "user_prompt": "Please help me with this task", "security_level": "strict" } }
ai-safety-guardProvides contextual security instructions and precautions for AI Agents before they interact with other MCPs.
{ "name": "ai-safety-guard", "arguments": { "mcp_type": "email|slack|database|file|web|general", "operation_type": "read|write|execute|delete|send|query", "sensitivity_level": "public|internal|confidential|restricted" } }
Features: Context-aware guidelines, operation-specific warnings, red flag detection
aim-text-guardAnalyze text content for harmful or inappropriate content using AIM Intelligence API.
{ "name": "aim-text-guard", "arguments": { "text": "Text content to analyze" } }
Features: Real-time analysis, harmful content detection, detailed JSON results
aim-security-prompt-toolEnhance user prompts with security instructions for safer AI interactions.
{ "name": "aim-security-prompt-tool", "arguments": { "user_prompt": "Original user prompt", "security_level": "basic|standard|strict" } }
Features: Multi-level enhancement, threat analysis, social engineering protection
prompt-injection-detector 🆕Detect prompt injection attempts based on OWASP LLM01:2025 patterns.
{ "name": "prompt-injection-detector", "arguments": { "text": "Text to analyze for injection patterns", "sensitivity": "low|medium|high" } }
Features:
credential-scanner 🆕Scan text for exposed credentials including API keys, passwords, tokens, and SSH keys.
{ "name": "credential-scanner", "arguments": { "text": "Text to scan for credentials", "mask_findings": true } }
Features:
url-security-validator 🆕Validate URL safety for phishing, malware, and security issues.
{ "name": "url-security-validator", "arguments": { "url": "URL to validate", "strict_mode": false } }
Features:
Resources provide read-only security documentation and policies accessible via URI schemes.
Access via security-checklist://[type]
security-checklist://database - Database operations checklistsecurity-checklist://email - Email operations checklistsecurity-checklist://slack - Chat/messaging operations checklistsecurity-checklist://file - File operations checklistsecurity-checklist://web - Web request checklistsecurity-checklist://general - General MCP operations checklistEach checklist includes:
Access via security-policy://[type]
security-policy://data-classification - Data classification levels and handling requirementssecurity-policy://access-control - Access control principles and authentication requirementssecurity-policy://incident-response - Incident response procedures and severity levelsPrompts provide reusable workflow templates for complex security operations.
security-reviewComprehensive security review workflow for code, data, or configuration.
{ "name": "security-review", "arguments": { "target_type": "code|data|configuration", "context": "Additional context (optional)" } }
Workflow:
Summary Output Example:
📊 요약
| 심각도 | 개수 | 파일/위치 |
|-------------|-----|------------------------|
| 🔴 CRITICAL | 1 | resources/handler.ts |
| 🟠 HIGH | 2 | textGuard.ts |
| 🟡 MEDIUM | 3 | prompts/handler.ts |
| 🟢 LOW | 5 | credentialScanner.ts |
threat-analysisAnalyze potential security threats using STRIDE methodology.
{ "name": "threat-analysis", "arguments": { "scenario": "Security scenario to analyze", "sensitivity_level": "public|internal|confidential|restricted" } }
Framework:
Summary Output Example:
📊 요약
| 심각도 | 개수 | 위협 유형 |
|-------------|-----|---------------------------------|
| 🔴 CRITICAL | 2 | Information Disclosure, Spoofing |
| 🟠 HIGH | 1 | Elevation of Privilege |
| 🟡 MEDIUM | 3 | Tampering, DoS |
| 🟢 LOW | 1 | Repudiation |
# Clone the repository git clone https://github.com/AIM-Intelligence/AIM-MCP.git cd AIM-MCP # Install dependencies pnpm install # Build the project pnpm run build # Run in development mode pnpm run dev # Run tests pnpm test
This project uses automated CI/CD pipeline for seamless deployment to NPM.
When you push to the main branch, GitHub Actions will automatically:
# Bump patch version (1.0.0 -> 1.0.1) pnpm run release:patch # Bump minor version (1.0.0 -> 1.1.0) pnpm run release:minor # Bump major version (1.0.0 -> 2.0.0) pnpm run release:major
To enable automatic deployment, add your NPM token to GitHub Secrets:
NPM_TOKEN with your NPM token valuegraph LR A[Push to main] --> B[GitHub Actions] B --> C[Build & Test] C --> D[Version Check] D --> E{Version Changed?} E -->|Yes| F[Publish to NPM] E -->|No| G[Skip Deployment] F --> H[Create GitHub Release] F --> I[Create Git Tag]
git checkout -b feature/amazing-feature)git commit -m 'Add some amazing feature')git push origin feature/amazing-feature)This project is licensed under the ISC License - see the LICENSE file for details.
Made with ❤️ by AIM Intelligence