1. Conduid
  2. AI
  3. Knowledge Graph Mia
MCP server · AI

Knowledge Graph Mia

Mia's MCP server enabling persistent memory for AI models through a local knowledge graph

Unclaimed ai
37Low

Scored 7 months ago · breakdown

About Knowledge Graph Mia

Knowledge Graph Mia is an MCP server published by miadisabelle in the AI category: mia's MCP server enabling persistent memory for AI models through a local knowledge graph.

The repository has 1 stars and 2 forks, with the last commit a month ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

Claude Code
claude mcp add knowledge-graph-mia -- npx -y mcp-knowledge-graph-mia
npx
npx -y mcp-knowledge-graph-mia

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Knowledge Graph Mia

Powered by Claude · Grounded in docs

I know everything about Knowledge Graph Mia. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

COAIA Memory - Creative-Oriented AI Assistant Memory System

MCP server implementing structural tension charts and advancing pattern support based on Robert Fritz's creative methodology

What is COAIA Memory?

COAIA Memory extends traditional knowledge graphs with structural tension charts - a powerful framework for organizing creative processes around desired outcomes rather than problem-solving. Based on Robert Fritz's structural tension methodology, it helps AI assistants maintain creative orientation and support advancing patterns.

Current Version: v2.3.0 (LLM-Intelligent Enhancement)

Key Features

🎯 Structural Tension Charts

  • Desired Outcomes: Clear, specific results you want to create
  • Current Reality: Honest assessment of where you are now
  • Structural Tension: The unresolved tension between current reality and desired outcome that naturally seeks resolution
  • Action Steps: Strategic secondary actions - intermediary end results that advance toward the primary goal
  • Due Dates: Time organization that creates momentum

🔭 Telescoping Support

  • Break down complex action steps into detailed sub-charts
  • Proper due date inheritance from parent steps
  • Hierarchical navigation between overview and details
  • Maintains structural tension at every level

📈 Advancing Pattern Tracking

  • Completed action steps become part of current reality, changing the structural dynamic
  • Each completion advances the system toward equilibrium (desired outcome)
  • Success creates new structural tension for continued advancement
  • Prevents oscillating patterns through proper structural design

🗣️ Natural Language Ready

  • Conversational patterns documented for intuitive interaction
  • Creative-oriented language (focus on creation vs problem-solving)
  • AI assistants can guide users through structural tension exercises

🔗 Traditional Knowledge Graph

  • Full entity, relation, and observation management
  • Search and retrieval capabilities
  • Compatible with existing MCP knowledge graph workflows

Installation & Usage

As NPX Package

npx coaia-memory --memory-path ./my-charts.jsonl

In Claude Desktop Config

{
  "mcpServers": {
    "coaia-memory": {
      "command": "npx",
      "args": ["-y", "coaia-memory", "--memory-path", "/path/to/your/charts.jsonl"],
      "autoapprove": [
        "create_structural_tension_chart",
        "telescope_action_step", 
        "mark_action_complete",
        "get_chart_progress",
        "list_active_charts",
        "create_entities",
        "create_relations",
        "add_observations"
      ]
    }
  }
}

Local Development

git clone <repository>
cd coaia-memory
npm install
npm run build

Core Tools

Structural Tension Chart Management

  • create_structural_tension_chart - Create new chart with outcome, reality, and action steps
  • telescope_action_step - Break down action steps into detailed sub-charts
  • mark_action_complete - Complete actions and update current reality
  • get_chart_progress - Monitor chart advancement
  • list_active_charts - Overview of all active charts

Traditional Knowledge Graph Operations

  • create_entities - Add new entities (people, concepts, events)
  • create_relations - Connect entities with relationships
  • add_observations - Record new information about entities
  • Plus full CRUD operations for entities, relations, and observations

Example Usage

Creating a Chart

// Natural language: "I want to learn Python web development in 6 weeks"
{
  "desiredOutcome": "Learn Python web development", 
  "currentReality": "I know basic Python but no web frameworks",
  "dueDate": "2025-09-15T00:00:00Z",
  "actionSteps": [
    "Complete Django tutorial",
    "Build practice project", 
    "Deploy something live"
  ]
}

Telescoping Detail

// Natural language: "Break down the Django tutorial step"
{
  "actionStepName": "chart_123_action_1",
  "newCurrentReality": "Never used Django, familiar with Python basics"
}

Tracking Progress

// Natural language: "I finished the Django tutorial"
{
  "actionStepName": "chart_123_action_1"
}

Creative Orientation Principles

Focus on Creation, Not Problem-Solving

  • Use: "I want to create...", "My desired outcome is..."
  • Avoid: "I need to fix...", "The problem is...", "I want to stop..."

Structural Tension Awareness

  • Always pair desired outcomes with current reality to create structural tension
  • This unresolved tension naturally seeks resolution through advancement
  • Action steps are strategic intermediary results that change the structural dynamic
  • Completed actions flow into current reality, creating new tension for continued advancement

Advancing Patterns

  • Success builds on success
  • Completed actions become part of current reality
  • Momentum creates natural progression toward goals

Development & Testing

Build & Test

npm install
npm run build

Test Environment

cd test-environment
claude-code  # Launch with pre-configured MCP setup

Release Status

✅ Validated in v2.0.0-rc.1

  • Core Structural Tension Charts: Fully functional with proper entity relationships
  • Telescoping Support: Action steps break down into sub-charts with due date inheritance
  • Advancing Pattern Tracking: Completions flow into current reality, system advances naturally
  • MCP Integration: All tools working correctly in Claude Code CLI environment
  • Real-World Testing: Validated with actual user interactions in test environment

Next Milestone

Guided Chart Creation: Transform from passive storage to active coaching system that helps users create meaningful structural tension charts with proper creative orientation validation.

Architecture

Enhanced Entity Types

  • structural_tension_chart - Container for chart components
  • desired_outcome - What you want to create
  • current_reality - Where you are now
  • action_step - Strategic actions with due dates

Creative Relations

  • creates_tension_with - Between current reality and desired outcome
  • advances_toward - Action steps advancing toward outcomes
  • telescopes_into - Hierarchical chart relationships
  • flows_into - Completed actions updating reality

Metadata Support

  • Due dates and completion tracking
  • Chart hierarchy and telescoping relationships
  • Creative phases (germination, assimilation, completion)
  • Timestamps and progress metrics

Credits

Philosophy

COAIA Memory embodies the principle that structure determines behavior. By organizing memory around structural tension rather than problem-solving patterns, it naturally supports creative advancement and helps users build the life they want to create.

The system recognizes that structural tension is the fundamental organizing principle of the creative process - not a problem to be solved, but a generative force to be harnessed.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Knowledge Graph Mia

How do I install Knowledge Graph Mia?

Run claude mcp add knowledge-graph-mia -- npx -y mcp-knowledge-graph-mia, then add the server to your MCP client's configuration.

Is Knowledge Graph Mia safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Knowledge Graph Mia still maintained?

Yes — the last commit was a month ago. The repository has 1 stars and 2 forks.