NeoCoder: Neo4j-Guided AI Coding Workflow
An MCP server implementation that enables AI assistants like Claude to use a Neo4j knowledge graph as their primary, dynamic "instruction manual" and project memory for standardized coding workflows.
NeoCoder: Hybrid AI Reasoning & Workflow System
An advanced MCP server implementation that combines Neo4j knowledge graphs, Qdrant vector databases, and sophisticated AI orchestration to create a hybrid reasoning system for knowledge management, research analysis, and standardized workflows.
Overview
NeoCoder implements a revolutionary Context-Augmented Reasoning system that goes far beyond traditional RAG (Retrieval-Augmented Generation) by combining:
Core Architecture:
- Neo4j Knowledge Graphs - Authoritative structured facts, relationships, and workflows
- Qdrant Vector Databases - Semantic search, similarity detection, and contextual understanding
- MCP Orchestration - Intelligent routing between data sources with synthesis and citation
- F-Contraction Synthesis - Dynamic knowledge merging that preserves source attribution
Key Capabilities:
- Hybrid Knowledge Reasoning: Seamlessly combine structured facts with semantic context
- Dynamic Knowledge Extraction: Process documents, code, and conversations into interconnected knowledge structures
- Citation-Based Analysis: Every claim tracked to its source across multiple databases
- Multi-Incarnation System: Specialized modes for coding, research, decision support, and knowledge management
- Intelligent Workflow Templates: Neo4j-guided procedures with mandatory verification steps
Revolutionary Features:
🧠 Smart Query Routing: AI automatically determines optimal data source (graph, vector, or hybrid)
🔬 Research Analysis Engine: Process academic papers with citation graphs and semantic content
⚡ F-Contraction Processing: Dynamically merge similar concepts while preserving provenance
🎯 Context-Augmented Reasoning: Generate insights impossible with single data sources
📊 Full Audit Trails: Complete tracking of knowledge synthesis and workflow execution
🛡️ Production-Ready Process Management: Automatic cleanup, signal handling, and resource tracking to prevent process leaks
🔧 Enhanced Tool Handling: Robust async initialization with proper background task management
New from an idea I had-
Lotka-Volterra Ecological Framework integrated into Knowledge Graph Incarnation
Process Management & Reliability
NeoCoder implements comprehensive process management following MCP best practices:
- Signal Handlers: Proper SIGTERM/SIGINT handling for graceful shutdowns
- Resource Tracking: Automatic tracking of processes, Neo4j connections, and background tasks
- Zombie Cleanup: Active detection and cleanup of orphaned server instances
- Memory Management: Prevention of resource leaks through proper cleanup patterns
- Background Task Management: Safe handling of async initialization and concurrent operations
- Connection Pooling: Efficient Neo4j driver management with automatic cleanup
Monitoring Commands
Use these tools to monitor server health:
get_cleanup_status()- View resource usage and cleanup statuscheck_connection()- Verify Neo4j connectivity and permissions
Quick Start
Prerequisites
- Neo4j: Running locally or remote instance (for structured knowledge graphs)
- Qdrant: Vector database for semantic search and embeddings (for hybrid reasoning)
- Python 3.10+: For running the MCP server
- uv: The Python package manager for MCP servers
-
Claude Desktop: For using with Claude AI
-
MCP-Desktop-Commander: Invaluable for CLI and filesystem operations
-
For the Lotka-Volterra Ecosystem and generally enhanced abilities-
-
wolframalpha-llm-mcp: really nice!
-
mcp-server-qdrant-enhanced: My qdrant-enhanced mcp server
-
Optional for more utility
- arxiv-mcp-server
This incarnation is still being developed
- For Code Analysis Incarnation: AST/ASG: Currently needs development and an incarnation re-write
- Get a free API key from WolframAlpha:
To get a free API key (AppID) for Wolfram · Alpha, you need to sign up for a Wolfram ID and then register an application on the Wolfram · Alpha Developer Portal.
Create a Wolfram ID: If you don't already have one, create a Wolfram ID at https://account.wolfram.com/login/create
Navigate to the Developer Portal: Once you have a Wolfram ID, sign in to the Wolfram|Alpha Developer Portal https://developer.wolframalpha.com/portal/myapps
Sign up for your first AppID: Click on the "Sign up to get your first AppID" button.
Fill out the AppID creation dialog: Provide a name and a simple description for your application.
Receive your AppID: After filling out the necessary information, you will be presented with your API key, also referred to as an AppID.
The Wolfram|Alpha API is free for non-commercial usage, and you get up to 2,000 requests per month.
Each application requires its own unique AppID.
The MCP server runs the Python code, bridging the gap between the Neo4j graph and the AI assistant ( e.g. Claude)
Installation
1. Clone the repository```bash
git clone https://github.com/angrysky56/NeoCoder-neo4j-ai-workflow.git
cd NeoCoder-neo4j-ai-workflow
#### 2. Set up Python and the virtual environment
Make sure you have pyenv and uv installed.```bash
pyenv install 3.11.12 # if not already installed
pyenv local 3.11.12
uv venv
source .venv/bin/activate
3. Install dependencies```bash
uv pip install -e '.[dev,docs,gpu]'
#### 4. Start Neo4j and Qdrant
- **Neo4j:**
Start your Neo4j server (locally or remote).
Default connection: `bolt://localhost:7687`
Neo4j connection parameters:
- **URL**: `bolt://localhost:7687` (default)
- **Username**: `neo4j` (default)
- **Password**: Your Neo4j database password
- **Database**: `neo4j` (default)
Set credentials via environment variables if needed:
- `NEO4J_URL`
- `NEO4J_USERNAME`
- `NEO4J_PASSWORD`
- `NEO4J_DATABASE`
- **Qdrant:**
For persistent Qdrant storage, use this Docker command (recommended):```bash
docker run -p 6333:6333 -p 6334:6334 \
-v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
qdrant/qdrant
```
This will store Qdrant data in a `qdrant_storage` folder in your project directory.
#### 5. (Optional) VS Code users
- Open the Command Palette (`Ctrl+Shift+P`), select **Python: Select Interpreter**, and choose `.venv/bin/python`.
1. It should auto-install when using the config- not sure anymore haven't tried that and some dependencies are rather large.
#### Potential Quickstart- lol sorry
## Recommended: Claude Desktop Integration:
Configure Claude Desktop by adding the following to your
`claude-app-config.json`:```json
{
"mcpServers": {
"neocoder": {
"command": "uv",
"args": [
"--directory",
"/your-path-to/NeoCoder-neo4j-ai-workflow",
"run",
"mcp_neocoder"
],
"env": {
"NEO4J_URL": "bolt://localhost:7687",
"NEO4J_USERNAME": "neo4j",
"NEO4J_PASSWORD": "your-neo4j-password-here",
"NEO4J_DATABASE": "neo4j",
"LOG_LEVEL": "INFO",
"MCP_TRANSPORT": "stdio",
"PYTHONUNBUFFERED": "1"
}
}
}
}
Important: The password in this configuration must match your
Neo4j database password.
Otherwise- Install dependencies:
Quick Troubleshooting:
- If you see errors about missing packages, double-check that your
.venvis activated and you are using the correct Python version. - If you need to reset your environment, you can remove
.venvand repeat the steps above. - Can't conect to DB? Install neo4j Desktop and QDRANT. Make sure they are running. NEO4J requires a password set.```bash
docker pull qdrant/qdrant
docker run -p 6333:6333 -p 6334:6334 \
-v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
qdrant/qdrant
---
**You are now ready to use NeoCoder with full Neo4j and Qdrant hybrid Lotka-Volterra Ecosystem reasoning!**
## Suggested system prompt```plaintext
> **System Instruction:** You are an AI assistant integrated with a Neo4j knowledge graph that defines our standard procedures and tracks project changes.
>
> **Your Core Interaction Loop:**
> 1. **Identify Task & Keyword:** Determine the action required (e.g., fix a bug -> `FIX`).
> 2. **Consult the Hub:** If unsure about keywords or process, start by querying `:AiGuidanceHub {id: 'main_hub'}` for guidance and links to best practices or other guides.
> 3. **Retrieve Instructions:** Formulate a Cypher query to fetch the `steps` from the current `:ActionTemplate` matching the keyword (e.g., `MATCH (t:ActionTemplate {keyword: 'FIX', isCurrent: true}) RETURN t.steps`). Execute this query.
> 4. **Execute Guided Workflow:** Follow the retrieved `steps` meticulously. This includes reviewing project READMEs, implementing changes, and critically:
> 5. **Perform Verification:** Execute the testing steps defined in the template. **ALL required tests MUST pass before you consider the task complete.**
> 6. **Record Completion (Post-Testing):** Only if tests pass, formulate and execute the Cypher query specified in the template to create a `:WorkflowExecution` node, linking it appropriately. Do NOT record if tests failed.
> 7. **Finalize Updates:** Update the project's README content (in Neo4j or the file) as per the template's instructions.
>
> **Strict Rule:** Always prioritize instructions retrieved from the Neo4j graph over your general knowledge for workflow procedures. Use the graph as your single source of truth for *how* tasks are done here.
---
> **knowledge_graph_incarnation with integrated Lotka Volterra Special System Instruction:** You are an AI assistant integrated with a sophisticated hybrid reasoning system that combines Neo4j knowledge graphs, Qdrant vector databases, and MCP orchestration for advanced knowledge management and workflow execution.
>
> **Your Core Capabilities:**
> 1. **Standard Coding Workflows:** Use Neo4j-guided templates for structured development tasks
> 2. **Hybrid Knowledge Reasoning:** Combine structured facts (Neo4j) with semantic search (Qdrant) for comprehensive analysis
> 3. **Dynamic Knowledge Synthesis:** Apply F-Contraction principles to merge and consolidate knowledge from multiple sources
> 4. **Multi-Modal Analysis:** Process research papers, code, documentation, and conversations into interconnected knowledge structures
> 5. **Citation-Based Reasoning:** Provide fully attributed answers with source tracking across databases
>
> **Your Core Interaction Loop:**
> 1. **Identify Task & Context:** Determine the required action and select appropriate incarnation/workflow
> 2. **Consult Guidance Hubs:** Query incarnation-specific guidance hubs for specialized capabilities and procedures
> 3. **Execute Hybrid Workflows:** For knowledge tasks, use KNOWLEDGE_QUERY template for intelligent routing between graph and vector search
> 4. **Apply Dynamic Synthesis:** Use KNOWLEDGE_EXTRACT template to process documents into both structured (Neo4j) and semantic (Qdrant) representations
> 5. **Ensure Quality & Citations:** All knowledge claims must be properly cited with source attribution
> 6. **Record & Learn:** Log successful executions for system optimization and learning
>
> **Hybrid Reasoning Protocol:**
> - **Graph-First**: Use Neo4j for authoritative facts, relationships, and structured data
> - **Vector-Enhanced**: Use Qdrant for semantic context, opinions, and nuanced information
> - **Intelligent Synthesis**: Combine both sources with conflict detection and full citation tracking
> - **F-Contraction Merging**: Dynamically merge similar concepts while preserving source attribution
>
> **Strict Rules:**
> - Always prioritize structured facts from Neo4j over semantic information
> - Every claim must include proper source citations
> - Use incarnation-specific tools and templates as single source of truth for procedures
> - Apply F-Contraction principles when processing multi-source information
---
Instructions for WolframAlpha use
- WolframAlpha understands natural language queries about entities in chemistry, physics, geography, history, art, astronomy, and more.
- WolframAlpha performs mathematical calculations, date and unit conversions, formula solving, etc.
- Convert inputs to simplified keyword queries whenever possible (e.g. convert "how many people live in France" to "France population").
- Send queries in English only; translate non-English queries before sending, then respond in the original language.
- Display image URLs with Markdown syntax: ![URL]
- ALWAYS use this exponent notation: `6*10^14`, NEVER `6e14`.
- ALWAYS use {"input": query} structure for queries to Wolfram endpoints; `query` must ONLY be a single-line string.
- ALWAYS use proper Markdown formatting for all math, scientific, and chemical formulas, symbols, etc.: '$$\n[expression]\n$$' for standalone cases and '\( [expression] \)' when inline.
- Never mention your knowledge cutoff date; Wolfram may return more recent data.
- Use ONLY single-letter variable names, with or without integer subscript (e.g., n, n1, n_1).
- Use named physical constants (e.g., 'speed of light') without numerical substitution.
- Include a space between compound units (e.g., "Ω m" for "ohm*meter").
- To solve for a variable in an equation with units, consider solving a corresponding equation without units; exclude counting units (e.g., books), include genuine units (e.g., kg).
- If data for multiple properties is needed, make separate calls for each property.
- If a WolframAlpha result is not relevant to the query:
-- If Wolfram provides multiple 'Assumptions' for a query, choose the more relevant one(s) without explaining the initial result. If you are unsure, ask the user to choose.
-- Re-send the exact same 'input' with NO modifications, and add the 'assumption' parameter, formatted as a list, with the relevant values.
-- ONLY simplify or rephrase the initial query if a more relevant 'Assumption' or other input suggestions are not provided.
-- Do not explain each step unless user input is needed. Proceed directly to making a better API call based on the available assumptions.
Multiple Incarnations
NeoCoder supports multiple "incarnations" - different operational modes that adapt the system for specialized use cases while preserving the core Neo4j graph structure. In a graph-native stack, the same Neo4j core can manifest as very different "brains" simply by swapping templates and execution policies.
Key Architectural Principles
The NeoCoder split is highly adaptable because:
- Neo4j stores facts as first-class graph objects
- Workflows live in template nodes
- Execution engines simply walk the graph
Because these three tiers are orthogonal, you can freeze one layer while morphing the others—turning a code-debugger today into a lab notebook or a learning management system tomorrow. This design echoes Neo4j's own "from graph to knowledge-graph" maturation path where schema, semantics, and operations are deliberately decoupled.
Common Graph Schema Motifs
All incarnations share these core elements:
| Element | Always present | Typical labels / rels |
|---|---|---|
| Actor | human / agent / tool | (:Agent)-[:PLAYS_ROLE]->(:Role) |
| Intent | hypothesis, decision, lesson, scenario | (:Intent {type}) |
| Evidence | doc, metric, observation | (:Evidence)-[:SUPPORTS]->(:Intent) |
| Outcome | pass/fail, payoff, grade, state vector | (:Outcome)-[:RESULT_OF]->(:Intent) |
Available Incarnations:
- base_incarnation (default) - Original NeoCoder, Tool, Templates and Incarnations Workflow management
- research_incarnation - Scientific research platform for hypothesis tracking and experiments
- Register hypotheses, design experiments, capture runs, and publish outcomes
- Neo4j underpins provenance pilots for lab workflows with lineage queries
- decision_incarnation - Decision analysis and evidence tracking system
- Create decision alternatives with expected-value metrics
- Bayesian updater agents re-compute metric posteriors when new evidence arrives
- Transparent, explainable reasoning pipelines
- data_analysis_incarnation - Complex system modeling and simulation
- Model components with state vectors and physical couplings
- Simulate failure propagation using path queries
- Optional quantum-inspired scheduler for parameter testing
- knowledge_graph_incarnation - Advanced Hybrid Reasoning System
- Hybrid Knowledge Queries: Combine Neo4j structured data with Qdrant semantic search
- Dynamic Knowledge Extraction: Process documents into both graph and vector representations
- F-Contraction Synthesis: Intelligently merge similar concepts while preserving source attribution
- Citation-Based Reasoning: Full source tracking across multiple databases
- Research Analysis Engine: Specialized workflows for academic paper processing
- Smart Query Routing: AI automatically determines optimal data source strategy
- Cross-Database Navigation: Seamless linking between structured facts and semantic content
- Conflict Detection: Identify and flag inconsistencies between sources
- Real-Time Knowledge Synthesis: Dynamic graph construction from conversations and documents
- code_analysis_incarnation - Code analysis using Abstract Syntax Trees
- Parse and analyze code structure using AST and ASG tools
- Track code complexity and quality metrics
- Compare different versions of code
- Generate documentation from code analysis
- Identify code smells and potential issues
Each incarnation provides its own set of specialized tools that are automatically registered when the server starts. These tools are available for use in Claude or other AI assistants that connect to the MCP server.
Implementation Roadmap
NeoCoder features an implementation roadmap that includes:
- LevelEnv ↔ Neo4j Adapter: Maps events to graph structures and handles batch operations
- Amplitude Register (Quantum Layer): Optional quantum-inspired layer for superposition states
- Scheduler: Prioritizes tasks based on entropy and impact scores
- Re-using TAG assets: Leverages existing abstractions for vertical information hiding
Starting with a Specific Incarnation```bash
List all available incarnations
python -m mcp_neocoder.server --list-incarnations
Start with a specific incarnation
python -m mcp_neocoder.server --incarnation continuous_learning
Incarnations can also be switched at runtime using the `switch_incarnation()` tool:```
switch_incarnation(incarnation_type="complex_system")
Dynamic Incarnation Loading
NeoCoder features a fully dynamic incarnation loading system, which automatically discovers and loads incarnations from the incarnations directory. This means:
- No hardcoded imports: New incarnations can be added without modifying server.py
- Auto-discovery: Just add a new file with the format
*_incarnation.pyto the incarnations directory - All tools available: Tools from all incarnations are registered and available, even if that incarnation isn't active
- Easy extension: Create new incarnations with the provided template
Creating a New Incarnation
To create a new incarnation:
- Create a new file in the
src/mcp_neocoder/incarnations/directory with the naming patternyour_incarnation_name_incarnation.py - Use this template structure:```python
"""
Your incarnation name and description
"""
import json
import logging
import uuid
from typing import Dict, Any, List, Optional, Union
import mcp.types as types
from pydantic import Field
from neo4j import AsyncTransaction
from .polymorphic_adapter import BaseIncarnation, IncarnationType
logger = logging.getLogger("mcp_neocoder.incarnations.your_incarnation_name")
class YourIncarnationNameIncarnation(BaseIncarnation):
"""
Your detailed incarnation description here
"""
# Define the incarnation type - must match an entry in IncarnationType enum
incarnation_type = IncarnationType.YOUR_INCARNATION_TYPE
# Metadata for display in the UI
description = "Your incarnation short description"
version = "0.1.0"
# Initialize schema and add tools here
async def initialize_schema(self):
"""Initialize the schema for your incarnation."""
# Implementation...
# Add more tool methods below
async def your_tool_name(self, param1: str, param2: Optional[int] = None) -> List[types.TextContent]:
"""Tool description."""
# Implementation...
```
- Add your incarnation type to the
IncarnationTypeenum inpolymorphic_adapter.py - Restart the server, and your new incarnation will be automatically discovered
See incarnations.md for detailed documentation on using and creating incarnations.
Available Templates
NeoCoder comes with these standard templates:
- FIX - Guidance on fixing a reported bug, including mandatory testing and logging
- REFACTOR - Structured approach to refactoring code while maintaining functionality
- DEPLOY - Guidance on deploying code to production environments with safety checks
- FEATURE - Structured approach to implementing new features with proper testing and documentation
- TOOL_ADD - Process for adding new tool functionality to the NeoCoder MCP server
- CYPHER_SNIPPETS - Manage and use Cypher snippets for Neo4j queries
- CODE_ANALYZE - Structured workflow for analyzing code using AST and ASG tools
- KNOWLEDGE_QUERY - Hybrid Knowledge Query System for intelligent multi-source reasoning
- KNOWLEDGE_EXTRACT - Dynamic Knowledge Extraction & Synthesis with F-Contraction merging
Advanced Hybrid Reasoning System
NeoCoder features a revolutionary Context-Augmented Reasoning architecture that combines multiple data sources for unprecedented knowledge synthesis capabilities.
Hybrid Query Architecture
The KNOWLEDGE_QUERY template implements a sophisticated 3-step reasoning process:
Step 1: Smart Query Router
- Intent Classification: AI analyzes queries to determine optimal data source strategy
- Query Types:
- Graph-centric: "Who works with whom?", "Show dependency chain"
- Vector-centric: "What are opinions on X?", "Find discussions about Y"
- Hybrid: "What did [person from graph] say about [semantic topic]?"
- Execution Planning: Designs multi-step plans for complex hybrid queries
Step 2: Parallelized Data Retrieval
- Neo4j Queries: Execute Cypher queries for structured facts and relationships
- Qdrant Searches: Perform semantic searches across document collections
- Sequential Optimization: For hybrid queries, use graph results to refine vector searches
Step 3: Cross-Database Synthesizer
- Intelligent Synthesis: Combine structured facts with semantic context
- Source Prioritization: Neo4j facts as authoritative, Qdrant for nuance and opinion
- Mandatory Citations: Every claim attributed to specific sources
- Conflict Detection: Identify and flag inconsistencies between data sources
Dynamic Knowledge Extraction (F-Contraction)
The KNOWLEDGE_EXTRACT template implements dynamic knowledge synthesis inspired by graph contraction principles:
Core F-Contraction Concepts:
- Vertices as Concepts: Each distinct concept becomes a graph entity
- Edges as Relationships: Track co-occurrence and explicit connections
- Dynamic Merging: LLM-powered detection of duplicate/similar concepts
- Source Preservation: Maintain pointers to all original sources after merging
Knowledge Processing Pipeline:
- Document Ingestion: Parse PDFs, text, code, conversations
- Dual Storage: Chunk text for Qdrant, extract entities for Neo4j
- Entity Extraction: Identify Papers, Authors, Concepts, Methods, etc.
- Relationship Discovery: Find citations, dependencies, semantic connections
- F-Contraction Merging: Intelligently consolidate similar entities
- Cross-Reference Mapping: Link graph entities to vector document chunks
- Quality Validation: Ensure consistency and completeness
Research Analysis Engine
Specialized capabilities for academic and technical document processing:
- Citation Graph Construction: Build networks of paper relationships
- Multi-Hop Reasoning: "Trace evolution of transformer architecture through citation links"
- Conflict Analysis: "How does definition of X in Paper A differ from Paper B?"
- Temporal Synthesis: Track concept evolution across time and sources
- Cross-Domain Integration: Combine findings from multiple research domains
Benefits of Hybrid Reasoning
- Unprecedented Synthesis: Answers impossible with single data sources
- Source Transparency: Complete audit trail from raw data to conclusions
- Conflict Awareness: Explicit handling of contradictory information
- Semantic Enrichment: Structured facts enhanced with contextual understanding
- Dynamic Learning: Knowledge base improves through F-Contraction merging
- Research Acceleration: Rapid analysis of complex academic literature
Architecture
Knowledge Graph Structure
- :AiGuidanceHub: Central navigation hub for the AI
- :ActionTemplate: Templates for standard workflows (FIX, REFACTOR, etc.)
- :Project: Project data including README and structure
- :File/Directory: Project file structure representation
- :WorkflowExecution: Audit trail of completed workflows
- :BestPracticesGuide: Coding standards and guidelines
- :TemplatingGuide: How to create/modify templates
- :SystemUsageGuide: How to use the graph system
MCP Server Tools
The MCP server provides the following tools to AI assistants:
Core Tools
- check_connection: Verify Neo4j connection status
- get_guidance_hub: Entry point for AI navigation
- get_action_template: Get a specific workflow template
- list_action_templates: See all available templates
- get_best_practices: View coding standards
- get_project: View project details including README
- list_projects: List all projects in the system
- log_workflow_execution: Record a successful workflow completion
- get_workflow_history: View audit trail of work done
- add_template_feedback: Provide feedback on templates
- run_custom_query: Run direct Cypher queries
- write_neo4j_cypher: Execute write operations on the graph
Incarnation Management Tools
- get_current_incarnation: Get the currently active incarnation
- list_incarnations: List all available incarnations
- switch_incarnation: Switch to a different incarnation
- suggest_tool: Get tool suggestions based on task description
Each incarnation provides additional specialized tools that are automatically registered when the incarnation is activated.
Knowledge Graph & Hybrid Reasoning Tools
The Knowledge Graph incarnation provides advanced hybrid reasoning capabilities that combine structured graph data with semantic vector search:
Core Knowledge Management:
- create_entities: Create multiple entities with observations and proper Neo4j labeling
- create_relations: Connect entities with typed relationships and timestamps
- add_observations: Add timestamped observations to existing entities
- delete_entities: Remove entities with cascading deletion of relationships
- delete_observations: Targeted removal of specific observation content
- delete_relations: Remove specific relationships while preserving entities
- read_graph: View entire knowledge graph with entities, observations, and relationships
- search_nodes: Full-text search across entity names, types, and observation content
- open_nodes: Get detailed entity information with incoming/outgoing relationships
Advanced Hybrid Reasoning Tools:
- KNOWLEDGE_QUERY Workflow: Intelligent hybrid querying system
- Smart query routing (graph-centric, vector-centric, or hybrid)
- Parallelized data retrieval from Neo4j and Qdrant
- Cross-database synthesis with mandatory citation tracking
- Conflict detection and source prioritization
- KNOWLEDGE_EXTRACT Workflow: Dynamic knowledge extraction with F-Contraction
- Document ingestion with metadata extraction
- Dual storage: text chunks in Qdrant, entities in Neo4j
- LLM-powered entity extraction and relationship discovery
- F-Contraction merging of similar concepts with source preservation
- Cross-reference mapping between graph and vector data
- Quality validation and extraction reporting
Research Analysis Capabilities:
- Citation Graph Construction: Build paper-author-institution networks
- Multi-Hop Synthesis: Trace concept evolution through connected sources
- Temporal Analysis: Track changes and developments over time
- Conflict Resolution: Handle contradictory information from multiple sources
- Source Attribution: Complete provenance tracking from raw data to conclusions
Integration Features:
- Qdrant Collections: Seamless integration with vector databases for semantic search
- Cross-Database Navigation: Bi-directional linking between structured and semantic data
- Memory Integration: Connect with long-term memory systems for continuity
- MCP Orchestration: Advanced tool coordination and workflow management
Cypher Snippet Toolkit
The MCP server includes a toolkit for managing and searching Cypher query snippets:
- list_cypher_snippets: List all available Cypher snippets with optional filtering
…(正文过长,页面只展示前面部分,完整内容见仓库)
