Smart MCP Server
About
The Smart MCP Server stands out from other tool orchestration or AI workflow systems in a few meaningful ways: Context Awareness: Unlike many workflow engines or tool servers that require explicit user input to select and run tools, Smart MCP Server automatically analyzes user m
Details
- License
- MIT
Explore
- 🛡️ Security: AES-256-CBC encryption with secure key management
- ✅ Compliance: Full MCP v1.0 and A2A v1.0 protocol compliance
- 🔄 Auto-Refresh: Automatic token validation and refresh
- 📊 Monitoring: Detailed token status and usage tracking
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Smart MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Node.js v18.0.0 or higher
- npm v7.0.0 or higher
- Google Gemini API Key (for AI features)
PORT=3000
NODE_ENV=production
LOG_LEVEL=info
The system automatically advertises its capabilities via public/agent.json:
{
"id": "smart-mcp-agent",
"name": "Smart MCP Agent",
"protocol_versions": {
"mcp": "1.0",
"a2a": "1.0"
},
"capabilities": [
"workflow_execution",
"token_management",
"model_interaction"
],
"supported_models": [
"gemini-2.5-pro",
"gpt-4",
"claude-3-opus"
]
}
npm install
- GitHub Integration: Repository management, analytics, and automation
- Stripe Integration: Payment processing and subscription management
- System Health Monitoring: Real-time system metrics and alerting
- Documentation Tools: Automated documentation consolidation and management
- GET /api/tools - List available MCP tools
- POST /api/tools/execute - Execute a tool with parameters
// Repository analytics
const stats = await tools.mcp_github_search_repositories({
query: "machine learning",
sort: "stars",
limit: 10
});
// Create pull request
const pr = await tools.mcp_github_create_pull_request({
owner: "username",
repo: "repository",
title: "Feature: Add new functionality",
body: "Description of changes",
head: "feature-branch",
base: "main"
});
// Get system metrics
const health = await tools.mcp_system_health_check();
console.log(health); // { cpu: 45, memory: 67, status: "healthy" }
// Monitor performance
const metrics = await tools.mcp_system_performance_metrics({
duration: "1h",
interval: "5m"
});
// Consolidate documentation
const docs = await tools.mcp_consolidate_documentation({
source: "./docs",
output: "./consolidated-docs.md",
format: "markdown"
});
The system intelligently selects tools based on context:
import { selectToolsForContext } from './src/context-aware-selector.js';
const context = {
message: "Help me optimize this database query",
history: ["SELECT * FROM users", "EXPLAIN ANALYZE"],
project: { type: "database", language: "SQL" }
};
const selectedTools = selectToolsForContext(context, availableTools);
// Returns: [database-tool, performance-tool, query-optimizer]
// Create a new MCP-compliant tool
export async function mcp_custom_tool(params) {
const { input, options = {} } = params;
try {
// Tool implementation
const result = await processInput(input, options);
return {
success: true,
result,
metadata: {
mcp_compliant: true,
execution_time: Date.now() - startTime
}
};
} catch (error) {
return {
success: false,
error: error.message,
metadata: { mcp_compliant: true }
};
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"smart mcp server": {
"smart-mcp-server": {
"command": "node",
"args": [
"examples/gemini-example.js"
]
}
}
}
}McpServers
{
"smart-mcp-server": {
"command": "node",
"args": [
"examples/gemini-example.js"
]
}
}A sophisticated, context-aware Model Context Protocol (MCP) server with Agent-to-Agent (A2A) protocol compliance. Features intelligent workflow execution, secure token management, and comprehensive AI model integration including Google's Gemini models.
🌟 Key Features
🔐 Secure Token Management
- MCP/A2A Compliant Tokens: Automatically generates and manages protocol-compliant API tokens - AES-256-CBC Encryption: Secure token storage with industry-standard encryption - Automatic Refresh: Intelligent token validation and refresh mechanisms - CLI Management: Easy token generation, validation, and monitoring via CLI tools🤖 Multi-Model AI Integration
- Gemini Models: Full integration with Google's Gemini 2.5 Pro, Gemini Pro, and embedding models - OpenAI Support: GPT-4, GPT-3.5 Turbo, and embedding models - Anthropic Integration: Claude 3 Opus, Sonnet, and Haiku models - Model-Agnostic Architecture: Unified interface across all AI providers🔄 Advanced Workflow System
- Dynamic Workflow Loading: Automatically loads workflow definitions from JSON files - Intelligent Execution: Uses AI function calling for optimal workflow selection - Progress Monitoring: Real-time execution tracking with metrics and logging - Error Recovery: Sophisticated error handling and retry mechanisms🌐 Protocol Compliance
- MCP v1.0: Full Model Context Protocol implementation - A2A v1.0: Agent-to-Agent protocol for multi-agent collaboration - Tool Discovery: Automatic tool registration and capability advertisement - Secure Communication: Encrypted inter-agent communication🛠️ Comprehensive Toolset
- GitHub Integration: Repository management, analytics, and automation - Stripe Integration: Payment processing and subscription management - System Health Monitoring: Real-time system metrics and alerting - Documentation Tools: Automated documentation consolidation and management🚀 Quick Start
Prerequisites
- Node.js v18.0.0 or higher
- npm v7.0.0 or higher
- Google Gemini API Key (for AI features)
Installation
1. Clone the repository:
git clone https://github.com/reconsumeralization/smart-mcp-server.git
cd smart-mcp-server
2. Install dependencies:
npm install
3. Generate MCP/A2A compliant tokens:
npm run token:generate
4. Start the server:
npm start
The server will start on port 3000 (configurable) with full MCP and A2A protocol support.
🔑 Token Management
CLI Commands
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
