NSAF MCP Server

{ "name": "nsaf-framework", "version": "1.0.0", "description": "Complete Neuro-Symbolic Autonomy Framework MCP Server", "author": "Bolorerdene Bundgaa", "contact": "bolor@ariunbolor.org", "website": "https://bolor.me", "server": { "command": "python3", "args": ["nsaf_mcp_server.py"], "env": { "PYTHONPATH": "." } }, "capabilities": { "tools": true, "resources": false, "prompts": false }, "categories": [ "AI Framework", "Quantum Computing", "Machine Learning", "Task Management", "Neural Networks", "Symbolic Reasoning" ], "tools": { "framework_management": [ "initialize_nsaf_framework", "get_nsaf_status", "shutdown_nsaf_framework" ], "task_processing": [ "process_complex_task", "get_task_status", "update_task_state" ], "quantum_symbolic": [ "cluster_tasks_quantum" ], "meta_agents": [ "evolve_agents_scma", "get_active_agents" ], "memory_system": [ "add_memory", "query_memory", "get_memory_metrics" ], "intent_projection": [ "project_intent_recursive" ], "human_ai_synergy": [ "synchronize_cognitive_state" ], "foundation_models": [ "generate_with_foundation_models", "get_embeddings" ], "system_analytics": [ "analyze_system_performance", "update_configuration", "get_configuration" ] }, "requirements": { "python": ">=3.9", "dependencies": [ "numpy>=1.26.0", "torch>=2.0.0", "qiskit>=2.0.0", "qiskit_aer>=0.17.0", "ray>=2.0.0", "rdflib>=7.0.0", "tensorflow>=2.20.0", "fastapi>=0.100.0", "yaml>=6.0", "networkx>=3.0", "scikit-learn>=1.6.0", "pandas>=2.3.0", "sympy>=1.12" ] }, "documentation": { "overview": "NSAF is a complete neuro-symbolic autonomy framework providing quantum-enhanced task processing, self-constructing meta-agents, hyper-symbolic memory, recursive intent projection, and human-AI synergy capabilities.", "features": [ "Multi-objective task decomposition and processing", "Quantum-symbolic clustering algorithms", "Self-constructing meta-agent evolution with distributed computing", "Hyper-symbolic memory with graph-based reasoning", "Recursive intent projection with neural networks", "Human-AI cognitive state synchronization", "Multi-provider foundation model integration", "Real-time system monitoring and analytics" ], "examples": [ { "name": "Process Complex Task", "tool": "process_complex_task", "description": "Process a multi-objective task like building a fraud detection system", "args": { "description": "Build an intelligent fraud detection system", "goals": [ {"type": "accuracy", "target": 0.95, "priority": 1.0}, {"type": "latency", "target": 50, "priority": 0.9} ], "constraints": [ {"type": "budget", "limit": 50000, "importance": 0.9} ] } }, { "name": "Project Future Intent", "tool": "project_intent_recursive", "description": "Project future states for an AI research assistant", "args": { "intent_description": "Build an autonomous AI research assistant", "projection_depth": 5, "confidence_threshold": 0.7 } }, { "name": "Evolve Specialized Agents", "tool": "evolve_agents_scma", "description": "Create optimized agents for neural architecture search", "args": { "task_description": "Optimize neural architecture search", "population_size": 20, "generations": 10 } } ] } }