Skip to main content
Glama

SDOF Knowledge Base

SDOF MCP - Structured Decision Optimization Framework

Node.js License: MIT MCP

Next-generation knowledge management system with 5-phase optimization workflow

The Structured Decision Optimization Framework (SDOF) Knowledge Base is a Model Context Protocol (MCP) server that provides persistent memory and context management for AI systems through a structured 5-phase optimization workflow.

๐Ÿš€ Quick Start

Prerequisites

  • Node.js 18+

  • OpenAI API Key (for embeddings)

  • MCP-compatible client (Claude Desktop, etc.)

Installation

# Clone the repository git clone https://github.com/your-username/sdof-mcp.git cd sdof-mcp # Install dependencies npm install npm run build # Configure environment cp .env.example .env # Edit .env with your OpenAI API key # Start the server npm start

๐Ÿ“– Documentation

โœจ Features

๐ŸŽฏ 5-Phase Optimization Workflow

  • Phase 1: Exploration - Solution discovery and brainstorming

  • Phase 2: Analysis - Detailed evaluation and optimization

  • Phase 3: Implementation - Code development and testing

  • Phase 4: Evaluation - Performance and quality assessment

  • Phase 5: Integration - Learning consolidation and documentation

๐Ÿง  Advanced Knowledge Management

  • Vector Embeddings: Semantic search with OpenAI embeddings

  • Persistent Storage: MongoDB/SQLite with vector indexing

  • Prompt Caching: Optimized for LLM efficiency

  • Schema Validation: Structured content types

  • Multi-Interface: Both MCP tools and HTTP API

๐Ÿ”ง Content Types

  • text - General documentation and notes

  • code - Code implementations and examples

  • decision - Decision records and rationale

  • analysis - Analysis results and findings

  • solution - Solution descriptions and designs

  • evaluation - Evaluation reports and metrics

  • integration - Integration documentation and guides

๐Ÿ› ๏ธ MCP Tools

Primary Tool: store_sdof_plan

Store structured knowledge with metadata:

{ plan_content: string; // Markdown content metadata: { planTitle: string; // Descriptive title planType: ContentType; // Content type (text, code, decision, etc.) tags?: string[]; // Categorization tags phase?: string; // SDOF phase (1-5) cache_hint?: boolean; // Mark for prompt caching } }

Example Usage

// Store a decision record { "server_name": "sdof_knowledge_base", "tool_name": "store_sdof_plan", "arguments": { "plan_content": "# Database Selection\n\nChose MongoDB for vector storage due to...", "metadata": { "planTitle": "Database Architecture Decision", "planType": "decision", "tags": ["database", "architecture"], "phase": "2", "cache_hint": true } } }

๐Ÿ—๏ธ Architecture

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ AI Clients โ”‚โ”€โ”€โ”€โ–ถโ”‚ SDOF Knowledge โ”‚โ”€โ”€โ”€โ–ถโ”‚ Database โ”‚ โ”‚ (Claude, etc.) โ”‚ โ”‚ Base MCP โ”‚ โ”‚ (MongoDB/ โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ Server โ”‚ โ”‚ SQLite) โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ–ผ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ HTTP API โ”‚ โ”‚ (Port 3000) โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

๐Ÿ”ง Configuration

MCP Client Configuration

Add to your MCP client configuration:

{ "mcpServers": { "sdof_knowledge_base": { "type": "stdio", "command": "node", "args": ["path/to/sdof-mcp/build/index.js"], "env": { "OPENAI_API_KEY": "your-openai-api-key" }, "alwaysAllow": ["store_sdof_plan"] } } }

Environment Variables

# Required OPENAI_API_KEY=sk-proj-your-openai-api-key # Optional EMBEDDING_MODEL=text-embedding-3-small HTTP_PORT=3000 MONGODB_URI=mongodb://localhost:27017/sdof

๐Ÿงช Testing

# Run tests npm test # Run system validation node build/test-unified-system.js # Performance benchmarks npm run test:performance

๐Ÿ“Š Performance

Target metrics:

  • Query Response: <500ms average

  • Embedding Generation: <2s per request

  • Vector Search: <100ms for similarity calculations

  • Database Operations: <50ms for CRUD operations

๐Ÿค Contributing

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/amazing-feature

  3. Make changes to TypeScript files in src/

  4. Run tests: npm test

  5. Build: npm run build

  6. Commit changes: git commit -m 'Add amazing feature'

  7. Push to branch: git push origin feature/amazing-feature

  8. Open a Pull Request

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ†˜ Support

๐ŸŽ‰ Success Indicators

You know the system is working correctly when:

  • โœ… No authentication errors in logs

  • โœ… store_sdof_plan tool responds successfully

  • โœ… Knowledge entries are stored and retrievable

  • โœ… Query performance meets targets (<500ms)

  • โœ… Test suite passes completely


Built with โค๏ธ for the AI community

-
security - not tested
A
license - permissive license
-
quality - not tested

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 persistent memory and context management for AI systems through a structured 5-phase optimization workflow.

  1. ๐Ÿš€ Quick Start
    1. Prerequisites
    2. Installation
  2. ๐Ÿ“– Documentation
    1. โœจ Features
      1. ๐ŸŽฏ 5-Phase Optimization Workflow
      2. ๐Ÿง  Advanced Knowledge Management
      3. ๐Ÿ”ง Content Types
    2. ๐Ÿ› ๏ธ MCP Tools
      1. Primary Tool: store_sdof_plan
      2. Example Usage
    3. ๐Ÿ—๏ธ Architecture
      1. ๐Ÿ”ง Configuration
        1. MCP Client Configuration
        2. Environment Variables
      2. ๐Ÿงช Testing
        1. ๐Ÿ“Š Performance
          1. ๐Ÿค Contributing
            1. ๐Ÿ“„ License
              1. ๐Ÿ†˜ Support
                1. ๐ŸŽ‰ Success Indicators

                  Related MCP Servers

                  • -
                    security
                    F
                    license
                    -
                    quality
                    Model Context Protocol (MCP) server implementation for semantic search and memory management using TxtAI. This server provides a robust API for storing, retrieving, and managing text-based memories with semantic search capabilities. You can use Claude and Cline AI Also
                    Last updated -
                    11
                    • Apple
                  • -
                    security
                    A
                    license
                    -
                    quality
                    A 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 -
                    6
                    10
                    MIT License
                    • Linux
                  • -
                    security
                    A
                    license
                    -
                    quality
                    A high-performance Model Context Protocol (MCP) server designed for large language models, enabling real-time communication between AI models and applications with support for session management and intelligent tool registration.
                    Last updated -
                    2
                    MIT License
                  • -
                    security
                    A
                    license
                    -
                    quality
                    Model 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 -
                    11
                    4
                    MIT License

                  View all related MCP servers

                  MCP directory API

                  We provide all the information about MCP servers via our MCP API.

                  curl -X GET 'https://glama.ai/api/mcp/v1/servers/tgf-between-your-legs/sdof-mcp'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server