NeoCoder-neo4j-ai-workflow
Verified Safeby angrysky56
Overview
NeoCoder is an MCP server designed to guide AI assistants, particularly for coding tasks, by providing structured instructions and project memory through a Neo4j knowledge graph. It supports polymorphic incarnations for various specialized workflows like research, decision support, data analysis, and code analysis, enhanced with Lotka-Volterra dynamics for diverse output selection.
Installation
uv --directory /home/ty/Repositories/NeoCoder-neo4j-ai-workflow run mcp_neocoderEnvironment Variables
- NEO4J_URL
- NEO4J_USERNAME
- NEO4J_PASSWORD
- NEO4J_DATABASE
- LOG_LEVEL
- MCP_TRANSPORT
- QDRANT_HOST
- QDRANT_PORT
- NEO4J_MAX_CONNECTIONS
Security Notes
The server relies on environment variables for Neo4j credentials, which is good practice. It utilizes `subprocess.run` for Docker commands (Qdrant setup) and process management (cleanup of zombie instances), which are powerful operations but are justified for system control in its intended local developer tool context. No direct `eval()` or un-sanitized external input leading to arbitrary code execution is immediately apparent in critical paths. However, extensive text generation and processing might open vectors if not handled carefully.
Similar Servers
mcp-neo4j
The Neo4j Cypher MCP server facilitates AI agent interaction with Neo4j graph databases by exposing Cypher query execution and schema retrieval as tools, supporting Text2Cypher workflows for data analysis and insights.
CodeGraphContext
An MCP server that indexes local code into a Neo4j graph database to provide real-time, accurate context and relationship analysis to AI assistants for understanding, writing, and refactoring code.
gemini-flow
An AI workflow orchestration and execution platform that enables visual programming and integrates with Google's Gemini and Vertex AI services.
codegraph-rust
CodeGraph transforms codebases into semantically searchable knowledge graphs, enabling AI agents to reason deeply about code for complex analysis tasks like dependency tracking, architectural understanding, and context building for new features.