CBCI MCP

CBCI MCP

Enables dynamic database querying through natural language questions using LLM-powered parameter extraction and template-based SQL generation. Supports flexible configuration for various domains and databases with automated response formatting.

Category
Visit Server

README

CBCI MCP

CBCI MCP (Model Context Protocol) - ChatBot CI with Dynamic Database Querying

이 패키지는 LLM을 활용한 동적 데이터베이스 질의응답 챗봇 시스템입니다.

설치

pip install cbci-mcp

사용법

기본 사용법

from cbci_mcp import CBCIMCPClient

# 클라이언트 생성
client = CBCIMCPClient()

# 서버 시작
client.start_server()

# 설정 (키워드 인수 지원)
client.setup(config="config.yaml", questions="questions.yaml", schema="schema.yaml")

# 질문하기
answer = client.ask("서울 2023년 학생수")
print(answer)

# 서버 종료
client.stop_server()

설정 파일 예시

config.yaml

# OpenAI API 설정
openai:
  api_key: "your-api-key-here"
  model: "gpt-4"
  temperature: 0.3
  max_tokens: 1000

# 데이터베이스 연결
database:
  host: "your-db-host"
  port: 25010
  user: "your-username"
  password: "your-password"
  database: "your-database"
  db_type: "db2"

# 챗봇 설정
chatbot:
  name: "데이터 분석 어시스턴트"
  show_sql: false
  show_technical_details: false
  max_history: 20

questions.yaml (예시)

qa_pairs:
  - id: "example_students"
    question: "학생수"
    keywords: ["학생수", "학생", "총", "전체"]
    sql_template: |
      SELECT SUM(A.STDNT_NOPE) AS TOTAL_STUDENTS 
      FROM YOUR_TABLE A 
      LEFT JOIN REGION_TABLE B ON A.RGN_CD = B.RGN_CD 
      WHERE 1=1
      {{REGION_FILTER}}
      {{YEAR_FILTER}}
    answer_template: "조건에 맞는 학생수는 {TOTAL_STUDENTS:,}명입니다."
    verified: true

sql_filters:
  REGION_FILTER: "AND B.RGN_NM = '{{RGN_NM}}'"
  YEAR_FILTER: "AND A.CRTR_YR = {{CRTR_YR}}"

matching:
  similarity_threshold: 0.3
  fallback_message: "죄송합니다. 해당 질문에 대한 정보를 찾을 수 없습니다."

schema.yaml (예시)

tables:
  students_table:
    description: "학생수 테이블"
    columns:
      RGN_CD: "지역 코드"
      CRTR_YR: "기준 연도"
      STDNT_NOPE: "학생수"

business_rules:
  join_patterns:
    - "지역 조회시: [데이터테이블] LEFT JOIN REGION_TABLE ON RGN_CD"
  data_structure:
    - "RGN_CD: 지역별 고유코드"
    - "CRTR_YR: 연도별 데이터"

API

CBCIMCPClient

__init__(server_script=None)

  • server_script: 서버 스크립트 경로 (기본값: 자동 감지)

start_server()

MCP 서버를 시작합니다.

stop_server()

MCP 서버를 종료합니다.

setup(config="config.yaml", questions="questions.yaml", schema="schema.yaml")

  • config: 설정 파일명
  • questions: 질문 템플릿 파일명
  • schema: 스키마 정보 파일명
  • 반환값: 설정 결과 딕셔너리

ask(question)

  • question: 질문 문자열
  • 반환값: 답변 문자열

get_questions()

  • 반환값: 사용 가능한 질문 목록

특징

  • LLM 파라미터 추출: 자연어 질문에서 자동으로 연도, 지역, 카테고리 등 추출
  • 동적 SQL 생성: 템플릿 기반으로 파라미터에 맞는 SQL 자동 생성
  • 유연한 설정: config, questions, schema 파일을 자유롭게 지정 가능
  • 키워드 인수 지원: 직관적인 setup 방식
  • 확장 가능: 다양한 도메인과 데이터베이스에 적용 가능

의존성

  • openai>=1.0.0: OpenAI API 클라이언트
  • pandas>=1.5.0: 데이터 처리
  • pyyaml>=6.0: YAML 설정 파일 처리
  • ibm-db>=3.1.0: DB2 데이터베이스 연결

라이선스

MIT License

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