partner-polaris

partner-polaris

Enables AI assistants to query, calculate, and benchmark AWS Partner Polaris training depth levels using CSV data.

Category
Visit Server

README

Partner Polaris MCP Server

AWS Partner Polaris Level 분석 MCP 서버. T&C 팀원들이 AI 어시스턴트를 통해 파트너 교육 깊이(Training Depth)를 조회, 계산, 벤치마크할 수 있습니다.

Tools

Tool Description
get_polaris_status 국가별 파트너 Polaris 레벨 현황 조회
calculate_polaris_level 입력값 기반 레벨 계산 (What-if 시뮬레이션)
get_l3_gap_analysis L3 달성 갭 분석 + 우선순위 액션 가이드
get_polaris_benchmark 국가간 Polaris 벤치마크 비교
get_polaris_criteria 공식 Polaris 프레임워크 기준 조회

설치

1. Clone

git clone https://github.com/twkim1122/polaris_mcp.git
cd polaris_mcp

2. Install

pip install -e .

Python 3.10+ 필요. 가상환경 사용 권장:

python -m venv .venv
.venv\Scripts\activate  # Windows
source .venv/bin/activate  # macOS/Linux
pip install -e .

3. 데이터 추가

data/ 폴더에 자국 파트너 데이터 CSV를 추가합니다:

cp data/sample_korea.csv data/japan.csv  # 템플릿 복사 후 수정

커스텀 경로를 사용하려면 환경변수를 설정합니다:

export POLARIS_DATA_DIR=/path/to/your/data  # macOS/Linux
set POLARIS_DATA_DIR=C:\path\to\your\data   # Windows

MCP 클라이언트 설정

Kiro

~/.kiro/settings/mcp.json:

{
  "mcpServers": {
    "partner-polaris": {
      "command": "python",
      "args": ["-m", "partner_polaris_mcp.server"],
      "cwd": "C:\\Users\\<your-alias>\\partner-polaris-mcp\\src",
      "env": {
        "POLARIS_DATA_DIR": "C:\\Users\\<your-alias>\\partner-polaris-mcp\\data"
      }
    }
  }
}

Claude Desktop

claude_desktop_config.json:

{
  "mcpServers": {
    "partner-polaris": {
      "command": "python",
      "args": ["-m", "partner_polaris_mcp.server"],
      "cwd": "C:\\Users\\<your-alias>\\partner-polaris-mcp\\src",
      "env": {
        "POLARIS_DATA_DIR": "C:\\Users\\<your-alias>\\partner-polaris-mcp\\data"
      }
    }
  }
}

Amazon Q Developer (VS Code)

.vscode/mcp.json:

{
  "servers": {
    "partner-polaris": {
      "command": "python",
      "args": ["-m", "partner_polaris_mcp.server"],
      "cwd": "${workspaceFolder}/src",
      "env": {
        "POLARIS_DATA_DIR": "${workspaceFolder}/data"
      }
    }
  }
}

데이터 포맷

CSV 컬럼

partner_name,tier,country,total_certs_ttm,foundational_certs,associate_certs,professional_certs,specialty_certs,ilt_sessions_total,ilt_sessions_int_plus,sb_subscription_engagements,sb_hands_on_completions,active_certs_3y

데이터 소스

  1. QuickSight "Global Partner Training & Certification" 대시보드
  2. Self Service - Partner Certifications 시트
  3. Candidate Country 필터 → 자국 선택 → Export

예시 질문

"Korea 파트너 Polaris 현황 보여줘"
"Samsung SDS가 L3 달성하려면 뭐가 필요해?"
"Korea vs Japan 파트너 교육 비교"
"Premier 파트너가 250 certs, 200 Int+ 이면 레벨이?"
"Advanced 티어의 L3 요건이 뭐야?"

Polaris 프레임워크 요약

Dual-Condition Rule

L2/L3 레벨 부여를 위해 두 조건 모두 충족 필요:

  • 조건1: Total certifications >= 티어별 threshold
  • 조건2: Engagement Points >= 티어별 threshold

Thresholds

Tier L2 Certs L2 Pts L3 Certs L3 Pts
Select 5 5 20 20
Advanced 10 10 40 40
Premier 100 100 400 400

Point 계산

  • L2 Points: ILT 1석 = 1pt, Cert 1개 = 1pt, SB Sub 5개 = 1pt
  • L3 Points: Int+ ILT 1석 = 1pt, Int+ Cert 1개 = 1pt, Hands-on SB 5개 = 1pt
  • Int+ = Associate + Professional + Specialty (Foundational 제외)

프로젝트 구조

partner-polaris-mcp/
├── src/partner_polaris_mcp/
│   ├── server.py          # MCP Tool 정의 (FastMCP)
│   ├── polaris_engine.py  # 레벨 계산 로직
│   ├── gap_analyzer.py    # L3 갭 분석 & 추천
│   ├── benchmark.py       # 국가간 벤치마킹
│   ├── data_loader.py     # CSV 로딩 & 캐싱
│   └── models.py          # 데이터 모델
├── data/
│   ├── polaris_criteria.json  # 레벨 threshold 설정
│   ├── sample_korea.csv       # 샘플 데이터
│   └── country_mapping.json   # 리전/국가 매핑
├── pyproject.toml
└── README.md

Contributing

  1. data/에 자국 CSV 추가
  2. get_polaris_status(country="YourCountry")로 테스트
  3. PR 또는 Slack #tc-polaris-mcp로 피드백

License

Internal AWS use only.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured