The AIM-Guard-MCP server provides AI-powered security tools for protecting AI agents during interactions with MCPs and external services.
AI Safety Guard: Provides contextual security instructions and precautions based on MCP type, operation, and data sensitivity levels.
Text Guard Analysis: Analyzes text content for harmful or inappropriate material using the AIM Intelligence API, delivering real-time safety assessments.
Security Prompt Enhancement: Enhances user prompts with security instructions at configurable levels (basic, standard, strict) to proactively prevent threats.
Integration: Works seamlessly with MCP-compatible AI assistants and connects to AIM Intelligence API for advanced analysis.
Customization: Supports customizable security levels and detailed reporting for secure AI interactions.
Mentioned in the context of repository management, GitHub releases, and as part of the development workflow
Used for automated CI/CD pipeline to build, test, and publish the MCP to NPM
Integrated for deployment workflow visualization in documentation
Integration for package deployment and publishing through NPM's registry
Used for package management in development workflow
Provides security guidelines and precautions for AI agents when interacting with Slack, ensuring safe message operations with appropriate sensitivity-level handling
Used as the implementation language for the MCP server
Integrated for validation of inputs and data structures
AIM Guard MCP
š”ļø 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.
Features
š”ļø AI Safety Guard: Provides contextual security instructions and precautions for AI Agents before MCP interactions
š Text Guard Analysis: Analyze text content for harmful or inappropriate content using AIM Intelligence API
š Security Prompt Enhancement: Add security instructions to user prompts for safer AI interactions
ā” Fast & Lightweight: Built with TypeScript and Zod validation
š§ Easy Integration: Works with any MCP-compatible AI assistant
š API Integration: Connects to AIM Intelligence API for advanced content analysis
Installation
Installing via Smithery
To install aim-mcp for Claude Desktop automatically via Smithery:
NPX (Recommended)
Global Installation
Local Installation
Usage
As MCP Server
Add to your MCP client configuration:
Testing the Tools
Test AI Safety Guard
Test Text Guard
Test Security Prompt Enhancement
Available Tools
1. ai-safety-guard
Provides contextual security instructions and precautions for AI Agents before they interact with other MCPs.
Features:
Context-aware security guidelines based on MCP type
Operation-specific warnings and precautions
Sensitivity-level protocols and restrictions
Comprehensive checklists for safe MCP interactions
Red flag detection and abort recommendations
2. aim-text-guard
Analyze text content for harmful or inappropriate content using AIM Intelligence API.
Features:
Real-time content analysis
Harmful content detection
Detailed analysis results in JSON format
Error handling with informative messages
Timestamp tracking for analysis requests
3. aim-security-prompt-tool
Enhance user prompts with security instructions for safer AI interactions.
Features:
Multi-level security enhancement (basic, standard, strict)
Comprehensive threat analysis instructions
Social engineering protection guidelines
Security policy compliance checks
Sanitization and validation requirements
Security Features
š”ļø AI Agent Protection
MCP Interaction Safety: Contextual guidelines for different MCP types
Operation Validation: Specific precautions for read/write/execute operations
Data Sensitivity Handling: Protocols based on data classification levels
š Content Analysis
Real-time Threat Detection: Analyze content for harmful patterns
API-powered Analysis: Advanced AI-driven content safety assessment
Comprehensive Reporting: Detailed security analysis results
š Prompt Security
Security-Enhanced Prompts: Add protective instructions to user prompts
Configurable Security Levels: Basic to strict security protocols
Threat Prevention: Proactive security measures in AI interactions
Development
Deployment
This project uses automated CI/CD pipeline for seamless deployment to NPM.
Automatic Deployment
When you push to the main
branch, GitHub Actions will automatically:
Build and Test: Compile TypeScript and run tests
Version Check: Compare current version with published version
Publish to NPM: Automatically publish if version has changed
Create Release: Generate GitHub release with version tag
Manual Version Management
Setting up NPM Token
To enable automatic deployment, add your NPM token to GitHub Secrets:
Go to npmjs.com and create an automation token
In your GitHub repository, go to Settings > Secrets and variables > Actions
Add a new secret named
NPM_TOKEN
with your NPM token value
Deployment Workflow
Contributing
Fork the repository
Create your feature branch (
git checkout -b feature/amazing-feature
)Commit your changes (
git commit -m 'Add some amazing feature'
)Push to the branch (
git push origin feature/amazing-feature
)Open a Pull Request
License
This project is licensed under the ISC License - see the LICENSE file for details.
Support
š§ Email: support@aim-intelligence.com
š Issues: GitHub Issues
š Documentation: GitHub Wiki
Made with ā¤ļø by AIM Intelligence
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
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.
Related Resources
Related MCP Servers
- -securityAlicense-qualityA Model Context Protocol (MCP) server that allows AI models to safely access and interact with local file systems, enabling reading file contents, listing directories, and retrieving file metadata.Last updated -610MIT License
- AsecurityAlicenseAqualityA server that uses the Model Context Protocol (MCP) to allow AI agents to safely execute shell commands on a host system.Last updated -1446MIT License
- -securityAlicense-qualityModel Context Protocol (MCP) server that provides AI assistants with advanced web research capabilities, including Google search integration, intelligent content extraction, and multi-source synthesis.Last updated -114MIT License