smart

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 messages, historical activity, and project context. This intelligent.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio reconsumeralization-smart-mcp-server node src/server.js \
  --env PORT="3000" \
  --env TLS_KEY_PATH="<path-to-key>" \
  --env TLS_CERT_PATH="<path-to-cert>" \
  --env GEMINI_API_KEY="<your-google-gemini-api-key>" \
  --env OPENAI_API_KEY="<your-openai-api-key>" \
  --env ANTHROPIC_API_KEY="<your-anthropic-api-key>"

How to use

Smart MCP Server is a feature-rich, context-aware MCP and A2A-compliant server designed to orchestrate AI workflows across multiple providers. It integrates Gemini, OpenAI, and Anthropic models under a unified interface, supports dynamic workflow loading from JSON definitions, and offers secure token management with encryption and automatic refresh. The server exposes a set of MCP and A2A endpoints for health checks, token management, workflow execution, and tool discovery, enabling agents to collaborate securely and efficiently. You can generate and manage MCP/A2A tokens via the built-in CLI, start the server to begin processing tasks, and monitor workflows in real time with logging and metrics.

How to install

Prerequisites:\n- Node.js v18.0.0 or higher\n- npm v7.0.0 or higher\n- Google Gemini API Key (for AI features)\n\nSteps:\n1. Clone the repository and install dependencies:\n\nbash\ngit clone https://github.com/reconsumeralization/smart-mcp-server.git\ncd smart-mcp-server\nnpm install\n\n\n2. Generate MCP/A2A compliant tokens (optional but recommended for first run):\n\nbash\nnpm run token:generate\n``\n\n3. Configure environment (example): create a .env file or export vars:\n\nbash\nexport GEMINI_API_KEY=<your-gemini-api-key>\nexport OPENAI_API_KEY=<your-openai-api-key>\nexport ANTHROPIC_API_KEY=<your-anthropic-api-key>\nexport PORT=3000\n\n\n4. Start the server:\n\nbash\nnpm start\n``\nThe server will begin listening on the configured port (default 3000).

Additional notes

Tips and considerations:\n- Ensure your Gemini/OpenAI/Anthropic API keys are valid and have the required permissions for the tasks you intend to run.\n- The server supports dynamic workflow definitions loaded from JSON files; place them under the configured workflows directory (per project conventions) for automatic discovery.\n- Tokens are stored securely with AES-256-CBC encryption; keep your encryption keys secure and rotate tokens periodically.\n- If you modify environment variables related to TLS, ensure your certificates and keys are correctly mounted and accessible by the server.\n- For debugging, inspect the /health and /api/logs endpoints and enable verbose logging in the configuration.\n- When running in production, consider containerization (Docker) or process managers (PM2, systemd) to ensure uptime and automatic restarts.

Related MCP Servers

TradingAgents mode

233

TradingAgents-MCPmode 是一个创新的多智能体交易分析系统，集成了 Model Context Protocol (MCP) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。

time

⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities

unity-editor

An MCP server and client for LLMs to interact with Unity Projects

website-publisher

AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.

xgmem

Global Memory MCP server, that manage all projects data.