ms82119/nifimcp

NiFi MCP (모델 컨텍스트 프로토콜)

이 저장소는 NiFi MCP 프로젝트를 포함합니다. 그것은 두 가지 방법으로 사용될 수 있습니다.

• Cursor AI, Claude Code, Antigravity 등과 같은 도구를 사용하는 일반 MCP 서버로 stdio를 통해 연결할 수 있습니다.
• 또는 내장 (이 저장소에 포함) 채팅 봇 브라우저에서 연결할 수 있습니다.

어떤 접근 방식을 통해 Apache NiFi 인스턴스와 상호 작용할 수 있습니다. 현재 30개의 공구가 있습니다, 건물, updating, running, debugging 및 문서화 nifi 교류를 덮는. 이것은 Nifi 버전 1.23 및 1.28로 테스트되었지만, Nifi REST Api와 같은 다른 버전에서 작동해야합니다.

내장 채팅 봇은 자신의 LLM API 키, 더 나은 모델을 공급해야하며 더 높은 토큰 컨텍스트를 선택할 수 있습니다. 그러나 Auto 모드에서 Cursor AI를 사용하는 것은 최고의 성능과 결과를 제공합니다. 나는 내 자신의 채팅 봇과 함께 구축 할 수있는 것보다 훨씬 더 나은 인터페이스가 될 것입니다. 그래서 나는 다른 옵션이 없다면 내장 채팅 봇을 추천합니다.

예제 대화 ( 내장 채팅 봇 사용)

NiFi MCP (Model Context Protocol)

This repository contains the NiFi MCP project. It can be used in two ways, either:

• As a plain MCP Server that tools like Cursor AI, Claude Code, Antigravity etc. can connect to via stdio
• Or, with a built-in (contained in this repo) chat bot that you can connect to from your browser.

Either approach allows you to interact with Apache NiFi instances using natural language. There are currently around 30 tools available, covering building, updating, running, debugging, and documenting nifi flows. This has been tested with Nifi versions 1.23 and 1.28, but should work on other versions like 2.x assuming the Nifi REST Api stays consistent.

The built-in chat bot requires you to supply your own LLM API keys, better models give better results and selecting higher token context can help too. I have however found that using Cursor AI in Auto mode gives the best performance and results. It turned out to be a much better interface than I could build with my own chat bot. So I only recommend the built-in chat bot if you have no other options.

Example Conversations (Using built-in chat bot)

• Build A New Flow From A Spec - See how the system creates a complete NiFi flow from requirements
• Debug An Existing Flow - Watch the system diagnose and fix issues in an existing flow

Recent Updates

Version 2.0 - Major UI Overhaul

• Added direct MCP server support for IDE’s like Cursor AI (best option)
• Enhanced the built in chatbot
  • Migrated from Streamlit to FastAPI/JavaScript client for improved performance and user experience
  • Enhanced real-time WebSocket communication for better workflow status updates
  • Improved message handling and duplicate message prevention
  • Modern, responsive UI with better accessibility and mobile support
  • Added a new workflow “Flow Documentation” to help generate better documentation about a flow

For the latest updates and release notes, see the GitHub Releases page.

Setup Instructions

Note: These instructions should also be followed after pulling a new version as there may be new package requirements.

Common Setup Steps (All Versions)

1. Clone the Repository:

   git clone [email protected]:ms82119/NiFiMCP.git
   cd NiFiMCP
   

2. Set Up a Virtual Environment: It’s recommended to use a virtual environment to manage dependencies. You can create one using venv:

   python3 -m venv .venv
   

3. Activate the Virtual Environment:

   • On macOS and Linux:

     source .venv/bin/activate
     

   • On Windows:

     .venv\Scripts\activate
     

4. Install Dependencies: Use uv to install dependencies based on pyproject.toml and uv.lock:

   uv sync