広告掲載
MCP.so
ログイン

NeoCoder: Neo4j-Guided AI Coding Workflow MCP Server

@angrysky56

リポジトリ

基本情報

カテゴリ

推論

ライセンス

MIT

トランスポート

stdio

作者

angrysky56

NeoCoder: Neo4j-Guided AI Coding Workflow MCP Server について

An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.

#neo4j#coder#claude#llm#mcp-server#vibe-coding

NeoCoder: Neo4j-Guided AI Coding Workflow MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "NeoCoder-neo4j-ai-workflow": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

NeoCoder: Neo4j-Guided AI Coding Workflow MCP Server のツール

12

Verify Neo4j connection status

Entry point for AI navigation

Get a specific workflow template

See all available templates

View coding standards

View project details including README

List all projects in the system

Record a successful workflow completion

View audit trail of work done

Provide feedback on templates

Run direct Cypher queries

Execute write operations on the graph

概要

What is NeoCoder: Neo4j-Guided AI Coding Workflow?

An MCP server that enables AI assistants like Claude to use a Neo4j knowledge graph and Qdrant vector database as a dynamic instruction manual and project memory for standardized coding workflows and hybrid reasoning.

How to use NeoCoder: Neo4j-Guided AI Coding Workflow?

Install prerequisites (Neo4j, Qdrant, Python 3.10+, uv, Claude Desktop), clone the repository, set up a virtual environment, install dependencies, start Neo4j and Qdrant, then configure Claude Desktop with the provided JSON config. Use the suggested system prompt to guide interactions. Monitor server health with get_cleanup_status() and check_connection() tools.

Key features of NeoCoder: Neo4j-Guided AI Coding Workflow

  • Hybrid knowledge reasoning combining Neo4j graphs and Qdrant vectors
  • Dynamic knowledge extraction from documents, code, and conversations
  • Citation-based analysis with full source attribution
  • Multi-incarnation system for coding, research, and decision support
  • Intelligent workflow templates with mandatory verification steps
  • Production-ready process management with automatic cleanup and signal handling

Use cases of NeoCoder: Neo4j-Guided AI Coding Workflow

  • Guided software development tasks using Neo4j-defined action templates
  • Research paper analysis with citation graphs and semantic content
  • Knowledge management with dynamic synthesis and structured storage
  • Decision support using context-augmented reasoning from multiple databases

よくある質問

1

What are the runtime dependencies?

Neo4j (local or remote), Qdrant (Docker recommended), Python 3.10+, uv, and Claude Desktop. Optional tools include WolframAlpha and AST MCP servers.

2

How do I configure Neo4j connection?

Set environment variables `NEO4J_URL`, `NEO4J_USERNAME`, `NEO4J_PASSWORD`, and `NEO4J_DATABASE` (defaults: bolt://localhost:7687, neo4j, neo4j, neo4j). The password must match your Neo4j database password.

3

How do I start Qdrant?

Run `docker run -p 6333:6333 -p 6334:6334 -v "$(pwd)/qdrant_storage:/qdrant/storage:z" qdrant/qdrant` for persistent storage.

4

Is the server production-ready?

Yes, it includes signal handlers, resource tracking, zombie cleanup, memory management, and background task management to prevent process leaks.

5

What transport does the MCP server use?

It uses `stdio` transport as configured via `MCP_TRANSPORT=1` in the environment.

コメント

「推論」の他のコンテンツ

quarkus-langchain4j-workshop

quarkusio

Quarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration

91

iFlytek Workflow MCP Server

iflytek

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

28

Proplan Mcp

King-Proplan

MCP server that gives Claude persistent project memory — roadmap, session history, and codebase context. Type continue and Claude picks up exactly where you left off

5

MCP Advanced Reasoning Server for Cursor AI

AzDeltaQQ

This is a very basic implementation of an Mcp-Reasoning-Server for Cursor AI .

13

Agentic Resource Discovery

neuronto

Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.

60
広告掲載