NeoCoder Neo4j Ai Workflow MCP Server

An MCP server implementation that enables AI assistants like Claude to use a Neo4j knowledge graph as their primary, dynamic "instruction manual" and

Local serverstdioPython

What is the NeoCoder Neo4j Ai Workflow MCP Server?

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.

What NeoCoder Neo4j Ai Workflow does

NeoCoder implements a revolutionary Context-Augmented Reasoning system that goes far beyond traditional RAG (Retrieval-Augmented Generation) by combining:

Requirements

  • 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

Practical notes

  • Maintained by angrysky56, written in Python.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
propose_toolPropose a new tool for the NeoCoder system
request_toolRequest a new tool feature as a user
get_tool_proposalGet details of a specific tool proposal
get_tool_requestGet details of a specific tool request
list_tool_proposalsList all tool proposals with optional filtering
list_tool_requestsList all tool requests with optional filtering

How to install the NeoCoder Neo4j Ai Workflow MCP Server

{
  "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",
        "NEO4J_DATABASE": "neo4j",
        "LOG_LEVEL": "INFO",
        "MCP_TRANSPORT": "stdio",
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

  • 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
VariableDescriptionRequired
NEO4J_URLDeclared in the maintainer’s client configuration.Check documentation
NEO4J_USERNAMEDeclared in the maintainer’s client configuration.Check documentation
NEO4J_PASSWORDDeclared in the maintainer’s client configuration.Check documentation
NEO4J_DATABASEDeclared in the maintainer’s client configuration.Check documentation
LOG_LEVELDeclared in the maintainer’s client configuration.Check documentation
MCP_TRANSPORTDeclared in the maintainer’s client configuration.Check documentation
PYTHONUNBUFFEREDDeclared in the maintainer’s client configuration.Check documentation

Example prompts to try

  • “Use NeoCoder Neo4j Ai Workflow to Prerequisites.”
  • “Use NeoCoder Neo4j Ai Workflow to Installation.”

Frequently asked questions

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 Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.