高度な認知分析、創造的な問題解決、構造化された思考のためのUnified Cognitive Processing Framework（UCPF）を実装したModel Context Protocol（MCP）サーバーです。
DeepLucid3D UCPFサーバーは、Unified Cognitive Processing FrameworkをMCPサーバーとして実装したものです。再帰的な自己認識と次元的な知識分類を組み合わせることで、問題解決と創造的思考に対する強力なアプローチを提供します。
このサーバーは、以下を支援する構造化された認知ツールを提供することで、AIの能力を拡張します：
認知状態の評価
知識次元のマッピング
再帰的な自己質問の適用
創造的な視点の生成
複雑な問題の分解と再統合
Related MCP server: Advanced Reasoning MCP Server
UCPFサーバーは、いくつかの主要な機能を通じて高度な認知処理を実現します：
認知状態評価: 問題解決中の自己認識を向上させるために、現在の認知状態（Dark Inertia、Passion、またはApproaching Lucidity）を特定します。
知識次元マッピング: 以下の3つの次元で知識をマッピングします：
認識（既知 vs 未知）
内容（既知の事実 vs 未知の事実）
アクセシビリティ（知る可能 vs 知る不可能）
再帰的自己質問: 初期の仮定に異議を唱え、潜在的な認知バイアスを特定します。
創造的視点生成: 新しい解決策を刺激するために、斬新な視点や比喩的な思考を生み出します。
問題分解: 複雑な問題を管理可能なコンポーネントに分解し、システム全体を意識しながら再統合します。
オプションの状態管理: 継続的な分析のためにセッション間のコンテキストを保持します。
Node.js (v14以上)
npm (v6以上)
Model Context Protocolと互換性のある環境
リポジトリをクローンする
git clone https://github.com/yourusername/DeepLucid3D-UCPF-Server.git
cd DeepLucid3D-UCPF-Server依存関係をインストールする
npm installプロジェクトをビルドする
npm run buildMCP設定を構成する
MCP設定ファイルにサーバーを追加します。Claude/Clineの場合、通常は以下の場所にあります：
Claude Desktopの場合: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
VSCode Clineの場合: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json (Linux)
以下の設定を追加してください：
{
"mcpServers": {
"ucpf": {
"command": "node",
"args": ["path/to/DeepLucid3D-MCP/build/index.js"],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}MCP互換アプリケーションを再起動する (Claude、VSCodeのClineなど)
このサーバーは、MCPを通じてアクセス可能な3つの主要ツールといくつかのリソースを公開しています：
analyze_problem: UCPFフレームワーク全体を通じて問題ステートメントを処理します
<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: トピックに関する斬新な視点や関連性を生成します
<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: UCPF処理の状態管理を制御します
<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>フレームワークのドキュメントにアクセスします：
<access_mcp_resource>
<server_name>ucpf</server_name>
<uri>ucpf://framework/overview</uri>
</access_mcp_resource>利用可能なリソース：
ucpf://framework/overview: UCPFフレームワークの概要
ucpf://framework/cognitive-states: 認知状態ガイド
ucpf://framework/knowledge-dimensions: 知識次元のリファレンス
ucpf://session/{sessionId}/analysis: 特定のセッションの分析結果
古典的ななぞなぞを解いてみましょう：「朝は4本足、昼は2本足、夕方は3本足で歩くものは何か？」
<use_mcp_tool>
<server_name>ucpf</server_name>
<tool_name>manage_state</tool_name>
<arguments>
{
"action": "enable"
}
</arguments>
</use_mcp_tool><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>分析により以下が提供されます：
認知状態の評価（比喩的な思考の可能性を特定する可能性が高い）
知っていることと知らないことの知識マッピング
初期の仮定に異議を唱えるための再帰的な質問（例：「文字通りの『足』を想定していないか？」）
さまざまな解釈に関する構造化された視点
<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>この探索により、以下が明らかになるかもしれません：
「足」を支柱構造とする比喩的な解釈
一日の時間を人生の段階とする比喩的な解釈
導き出される古典的な答え：人間。赤ちゃんとして4本の手足で這い、大人として2本足で歩き、老人になると杖（3本目の「足」）を使う。
<access_mcp_resource>
<server_name>ucpf</server_name>
<uri>ucpf://session/sphinx-riddle/analysis</uri>
</access_mcp_resource>これは完全な分析の旅路を提供し、フレームワークが構造化された認知処理を通じてどのように解決策に導いたかを示します。
このプロジェクトは巨人の肩の上に立っています：
AIシステムが外部ツールやリソースにアクセスできるようにする基盤プロトコルを作成した**Model Context Protocol (MCP)**チーム
MCPを活用できる高度なAIシステムに取り組んでいるAnthropic Claudeチーム
認知分析手法を支えるUnified Cognitive Processing Frameworkの概念への貢献者
このようなプロジェクトを可能にするライブラリやツールを提供してくれたオープンソースコミュニティ
MIT License
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
TranscriptionTools-MCP — トランスクリプト処理
DeepLucid3D-MCP — 認知処理
UNO-MCP — ナラティブ強化
gitea-mcp — Gitea統合
zero-vector-MCP — 手続き型生成
Process a problem statement through the full UCPF framework
| Name | Required | Description | Default |
|---|---|---|---|
| detailed | No | Whether to include detailed analysis | |
| enable_state | No | Whether to enable state management for this analysis | |
| problem | Yes | The problem statement to analyze | |
| session_id | No | Optional session ID for maintaining state between calls |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'process' and 'full UCPF framework', implying analysis or transformation, but doesn't describe what the tool actually does behaviorally—such as whether it performs computations, returns structured data, has side effects, or requires specific permissions. This leaves significant gaps in understanding the tool's operation and impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. It directly states the action and resource, making it easy to parse and understand quickly, with no wasted information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity implied by 'full UCPF framework' and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how it handles state or detailed analysis, or its behavioral traits, leaving the agent with insufficient context to use the tool effectively beyond basic parameter input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all four parameters. The description adds no additional meaning beyond what the schema provides, such as explaining how parameters interact with the UCPF framework or typical use cases. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'processes a problem statement through the full UCPF framework', which provides a clear verb ('process') and resource ('problem statement') with a specific methodology ('UCPF framework'). However, it doesn't differentiate from sibling tools like 'creative_exploration' or 'manage_state', leaving the specific scope of 'full UCPF framework' somewhat vague compared to alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling tools 'creative_exploration' or 'manage_state'. It lacks explicit context, prerequisites, or exclusions, leaving the agent to infer usage based on the tool name and description alone without clear alternatives or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate novel perspectives and connections for a topic
| Name | Required | Description | Default |
|---|---|---|---|
| constraints | No | Optional constraints or parameters to consider | |
| include_metaphors | No | Whether to include metaphorical thinking | |
| perspective_count | No | Number of perspectives to generate | |
| session_id | No | Optional session ID for maintaining state between calls | |
| topic | Yes | The topic or problem to explore creatively |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions generating 'novel perspectives and connections,' which implies a creative, non-destructive process, but fails to detail aspects like rate limits, authentication needs, output format, or whether it maintains state (e.g., via session_id). For a tool with no annotations, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Generate novel perspectives and connections for a topic.' It is front-loaded with the core action and resource, with no wasted words. This makes it easy to parse and understand quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 parameters, no output schema, no annotations), the description is incomplete. It lacks details on behavioral traits, output format, and how parameters interact, which are crucial for an AI agent to use it effectively. Without annotations or an output schema, the description should provide more context to compensate, but it does not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning all parameters are documented in the schema. The description adds no additional meaning beyond what the schema provides, such as explaining how 'constraints' affect generation or what 'perspective_count' entails. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Generate novel perspectives and connections for a topic.' It specifies the verb ('generate') and resource ('perspectives and connections'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'analyze_problem' or 'manage_state', which might also involve topic exploration or state management.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There is no mention of when to choose 'creative_exploration' over 'analyze_problem' or 'manage_state', nor any context about prerequisites or exclusions. This leaves the agent without clear usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Control the state management for UCPF processing
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | The state management action to perform | |
| session_id | No | Optional session ID to target a specific session |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'control' and actions like 'enable', 'disable', 'reset', and 'status', implying mutation capabilities, but doesn't specify permissions needed, side effects (e.g., data loss on reset), rate limits, or response format. This leaves critical behavioral traits undocumented for a tool that appears to modify system state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a tool with two parameters, though it could be more front-loaded with key details given the lack of annotations and output schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity implied by state management actions (including mutations like 'disable' and 'reset'), no annotations, and no output schema, the description is incomplete. It doesn't cover behavioral risks, response expectations, or error conditions, leaving significant gaps for the agent to operate safely and effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with clear documentation for both parameters (action with enum values and optional session_id). The description adds no additional parameter semantics beyond what the schema provides, such as explaining what 'reset' entails or when to use session_id. This meets the baseline of 3 since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'Control[s] the state management for UCPF processing', which provides a general purpose (state management) and domain (UCPF processing) but lacks specificity about what 'state management' entails or what resources are affected. It doesn't distinguish from sibling tools like 'analyze_problem' or 'creative_exploration', leaving the agent to infer differences based on tool names alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, typical scenarios, or exclusions, and there's no comparison to sibling tools. The agent must rely solely on the tool name and input schema to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0analyze_problemcreative_explorationmanage_stateScored across 3 tools
Each tool has a clearly distinct purpose: analyze_problem handles problem statement processing, creative_exploration generates novel perspectives, and manage_state controls state management. There is no overlap in functionality, making tool selection straightforward for an agent.
The tools follow a consistent verb_noun pattern (analyze_problem, creative_exploration, manage_state), which is predictable and readable. The minor deviation is that 'manage_state' uses a verb_noun structure while the others are adjective_noun or verb_noun, but overall consistency is maintained.
With only 3 tools, the set feels thin for a server named 'DeepLucid3D UCPF Server,' which suggests a complex framework. While each tool seems essential, the low count may limit coverage of the UCPF domain, potentially requiring agents to work around missing operations.
Inferred domain is UCPF (Unified Creative Problem Framework) processing, but the tool set has significant gaps. It lacks core operations like retrieving results, updating analyses, or deleting states, which could lead to agent failures in handling full problem-solving lifecycles. The surface is incomplete for the stated purpose.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
An MCP server for deep research or task groups
MCP server exposing Kettle Logic insight articles & industry guidance as tools + resources.
MCP server for generating rough-draft project plans from natural-language prompts.
