DeepLucid3D UCPF Server
An MCP server for advanced cognitive analysis, creative problem-solving, and structured thinking using the UCPF framework.
DeepLucid3D UCPF Server
A Model Context Protocol (MCP) server implementing the Unified Cognitive Processing Framework (UCPF) for advanced cognitive analysis, creative problem-solving, and structured thinking.
What is it?
The DeepLucid3D UCPF Server is an implementation of the Unified Cognitive Processing Framework as an MCP server. It combines recursive self-awareness with dimensional knowledge categorization to provide a powerful approach to problem-solving and creative thinking.
This server extends AI capabilities by providing structured cognitive tools that help:
- Assess cognitive states
- Map knowledge dimensions
- Apply recursive self-questioning
- Generate creative perspectives
- Decompose and reintegrate complex problems
What it does
The UCPF Server enables advanced cognitive processing through several key features:
Core Capabilities
-
Cognitive State Assessment: Identifies current cognitive states (Dark Inertia, Passion, or Approaching Lucidity) to improve self-awareness during problem-solving.
-
Knowledge Dimension Mapping: Maps knowledge across three dimensions:
- Awareness (Known vs. Unknown)
- Content (Knowns vs. Unknowns)
- Accessibility (Knowable vs. Unknowable)
-
Recursive Self-Questioning: Challenges initial assumptions and identifies potential cognitive biases.
-
Creative Perspective Generation: Produces novel viewpoints and metaphorical thinking to inspire new solutions.
-
Problem Decomposition: Breaks complex problems into manageable components and reintegrates them with awareness of the whole system.
-
Optional State Management: Maintains context between sessions for ongoing analysis.
Setup and Installation
Prerequisites
- Node.js (v14 or higher)
- npm (v6 or higher)
- An environment compatible with the Model Context Protocol
Installation Steps
-
Clone the repository
git clone https://github.com/yourusername/DeepLucid3D-UCPF-Server.git cd DeepLucid3D-UCPF-Server -
Install dependencies
npm install -
Build the project
npm run build -
Configure MCP settings
Add the server to your MCP settings file. For Claude/Cline, this is typically located at:
- For Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) - For VSCode Cline:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json(Linux)
Add the following configuration:
{ "mcpServers": { "ucpf": { "command": "node", "args": ["path/to/DeepLucid3D-MCP/build/index.js"], "env": {}, "disabled": false, "autoApprove": [] } } } - For Claude Desktop:
-
Restart your MCP-compatible application (Claude, VSCode with Cline, etc.)
How to Use
The server exposes three main tools and several resources that can be accessed through MCP:
Tools
-
analyze_problem: Process a problem statement through the full UCPF framework
<use_mcp_tool> <server_name>ucpf</server_name> <tool_name>analyze_problem</tool_name> <arguments> { "problem": "Your problem statement here", "session_id": "optional-session-id", "enable_state": false, "detailed": false } </arguments> </use_mcp_tool> -
creative_exploration: Generate novel perspectives and connections for a topic
<use_mcp_tool> <server_name>ucpf</server_name> <tool_name>creative_exploration</tool_name> <arguments> { "topic": "Your topic here", "constraints": ["Optional constraint 1", "Optional constraint 2"], "perspective_count": 3, "include_metaphors": true } </arguments> </use_mcp_tool> -
manage_state: Control state management for UCPF processing
<use_mcp_tool> <server_name>ucpf</server_name> <tool_name>manage_state</tool_name> <arguments> { "action": "enable", // or "disable", "reset", "status" "session_id": "optional-specific-session-id" } </arguments> </use_mcp_tool>
Resources
Access framework documentation:
<access_mcp_resource>
<server_name>ucpf</server_name>
<uri>ucpf://framework/overview</uri>
</access_mcp_resource>
Available resources:
ucpf://framework/overview: Overview of the UCPF frameworkucpf://framework/cognitive-states: Guide to cognitive statesucpf://framework/knowledge-dimensions: Reference for knowledge dimensionsucpf://session/{sessionId}/analysis: Analysis results for a specific session
Example Use Case: Using UCPF to Solve a Riddle
Let's solve the classic riddle: "What walks on four legs in the morning, two legs in the afternoon, and three legs in the evening?"
Step 1: Enable state management for session persistence
<use_mcp_tool>
<server_name>ucpf</server_name>
<tool_name>manage_state</tool_name>
<arguments>
{
"action": "enable"
}
</arguments>
</use_mcp_tool>
Step 2: Analyze the riddle using the UCPF framework
<use_mcp_tool>
<server_name>ucpf</server_name>
<tool_name>analyze_problem</tool_name>
<arguments>
{
"problem": "What walks on four legs in the morning, two legs in the afternoon, and three legs in the evening?",
"session_id": "sphinx-riddle",
"enable_state": true
}
</arguments>
</use_mcp_tool>
The analysis will provide:
- Cognitive state assessment (likely identifying potential metaphorical thinking)
- Knowledge mapping of what we know and don't know
- Recursive questions to challenge initial assumptions (e.g., "Are we assuming literal legs?")
- Structured perspectives on different interpretations
Step 3: Explore creative perspectives to find the solution
<use_mcp_tool>
<server_name>ucpf</server_name>
<tool_name>creative_exploration</tool_name>
<arguments>
{
"topic": "Walking with different numbers of legs at different times of day",
"constraints": ["morning", "afternoon", "evening", "four", "two", "three"],
"include_metaphors": true,
"session_id": "sphinx-riddle"
}
</arguments>
</use_mcp_tool>
This exploration might reveal:
- The metaphorical interpretation of "legs" as support structures
- The metaphorical interpretation of times of day as stages of life
- Leading to the classic answer: a human, who crawls on four limbs as a baby, walks on two legs as an adult, and uses a cane (third "leg") in old age
Step 4: Review the session analysis
<access_mcp_resource>
<server_name>ucpf</server_name>
<uri>ucpf://session/sphinx-riddle/analysis</uri>
</access_mcp_resource>
This provides the complete analysis journey, showing how the framework led to the solution through structured cognitive processing.
Acknowledgments
This project stands on the shoulders of giants:
- The Model Context Protocol (MCP) team for creating the foundational protocol that enables AI systems to access external tools and resources
- The Anthropic Claude team for their work on advanced AI systems capable of utilizing MCP
- Contributors to the Unified Cognitive Processing Framework concepts that power the cognitive analysis methodology
- The open-source community whose libraries and tools make projects like this possible
License
MIT License
Project Structure
DeepLucid3D-UCPF-Server/
├── src/
│ ├── engine/
│ │ ├── ucpf-core.ts # Core UCPF processing logic
│ │ ├── creative-patterns.ts # Creative thinking utilities
│ │ └── state-manager.ts # Session state management
│ ├── tools/
│ │ ├── analyze-problem.ts # Problem analysis tool
│ │ └── creative-exploration.ts # Creative exploration tool
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript files
├── package.json # Project dependencies and scripts
└── README.md # This documentation
© 2025 DeepLucid3D UCPF Server
Serveurs connexes
LivePilot
AI copilot for Ableton Live 12 — 91 MCP tools for real-time music production, sound design, and mixing
Todoist
Interact with the Todoist API to manage your tasks using natural language.
CData Jira Service Management
A read-only server to query live Jira Service Management data via a simple MCP interface, powered by CData.
Promptheus
AI-powered prompt refinement tool with adaptive questioning and multi-provider support. Intelligently refines prompts through clarifying questions, supports 6+ AI providers (Google Gemini, Anthropic Claude, OpenAI, Groq, Alibaba Qwen, Zhipu GLM), and provides comprehensive prompt engineering capabilities.
Claude Desktop
Integrates Amoga Studio with Claude Desktop for enhanced productivity and communication.
Graph MCP
An MCP to interact with Office 365 - Teams, mail, calendar.
WxO Agent MCP
Simple MCP (Model Context Protocol) server that invokes a single Watson Orchestrate agent remotely. The agent is defined once via environment variables or MCP config. Use this when you want a lightweight MCP that only chats with one agent—no tool management, no agent listing, no flows. Just invoke_agent(message) and get_agent().
notebooklm MCP
Chat with Google NotebookLM via MCP or HTTP REST API for zero-hallucination answers from your docs. Perfect for n8n workflows and automation.
Logseq MCP Tools
An MCP server that allows AI agents to interact with a local Logseq instance.
Pleasanter MCP Server
An MCP server for interacting with the Pleasanter low-code/no-code business application platform.