Skip to main content
Glama

cloudflare-mcp v1.0.0

전체 Cloudflare 생태계를 위한 범용 Model Context Protocol (MCP) 서버입니다. 16개의 분산된 원격 MCP 엔드포인트를 단일 고성능 로컬 서버로 대체합니다.

기능 (7가지 통합 도구)

  • cf_dns: 영역(Zone), DNS 레코드(A, CNAME, TXT, MX 등), CDN 캐시 제거

  • cf_compute: Cloudflare Workers, KV 키-값 저장소, 서버리스 D1 SQL 데이터베이스 실행

  • cf_storage: R2 객체 스토리지 버킷, Vectorize 벡터 데이터베이스 쿼리

  • cf_ai: Workers AI 추론(Llama, DeepSeek, Embeddings), AI Gateway 로그 및 텔레메트리

  • cf_security: Zero Trust 터널(cloudflared), WAF 방화벽 규칙, 감사 로그

  • cf_radar: Radar URL 스캐너, 글로벌 트래픽/공격 분석, GraphQL 쿼리

  • cf_api: 범용 REST API 게이트웨이(2,500개 이상의 Cloudflare 엔드포인트에 직접 액세스)

Related MCP server: mcp-server-cloudflare

구성

환경 변수에 Cloudflare API 토큰을 설정하거나 ~/.secrets/cloudflare-token.txt에 저장하세요:

export CLOUDFLARE_API_TOKEN="your-cloudflare-api-token"
export CLOUDFLARE_ACCOUNT_ID="your-account-id"  # Optional, automatically discovered if omitted

MCP 클라이언트 설치 (Claude Desktop, OpenCode, Cursor, Windsurf)

옵션 1: uvx로 즉시 설치 (권장)

{
  "mcpServers": {
    "cloudflare": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/Steph-ux/cloudflare-mcp.git", "cloudflare-mcp"]
    }
  }
}

옵션 2: pip install 사용

pip install git+https://github.com/Steph-ux/cloudflare-mcp.git

그런 다음 MCP 구성에 추가하세요:

{
  "mcpServers": {
    "cloudflare": {
      "command": "cloudflare-mcp"
    }
  }
}

옵션 3: 로컬 클론 (개발)

{
  "mcpServers": {
    "cloudflare": {
      "command": "python",
      "args": ["D:\\Steph\\script\\cloudflare-mcp\\server.py"]
    }
  }
}

사용 예시

1. DNS 관리

# List zones:
cf_dns(action='list_zones')

# Create DNS record:
cf_dns(
    action='create_record',
    zone_id='example.com',
    type='A',
    name='api',
    content='192.168.10.1',
    proxied=True
)

# Purge CDN cache:
cf_dns(action='purge_cache', zone_id='example.com', purge_everything=True)

2. D1 SQL 데이터베이스 및 Workers

# Query D1 SQL database:
cf_compute(
    action='d1_query',
    database_id='YOUR_D1_DATABASE_ID',
    sql='SELECT * FROM users WHERE active = 1 LIMIT 10;'
)

# Store key-value in KV:
cf_compute(
    action='kv_put',
    namespace_id='YOUR_KV_NAMESPACE_ID',
    key_name='session_token',
    value='xyz123'
)

3. R2 객체 스토리지

# List buckets:
cf_storage(action='list_r2')

# Create bucket:
cf_storage(action='create_r2', bucket_name='my-app-assets', location_hint='weur')

4. Workers AI 추론

# Run Llama 3 on Cloudflare edge:
cf_ai(
    action='run_model',
    model='@cf/meta/llama-3.1-8b-instruct',
    prompt='Write a python snippet for async retry logic.'
)

5. Radar URL 스캔 및 보안

# Scan URL for malware & phishing via Cloudflare Radar:
cf_radar(action='scan_url', url='https://target-to-scan.com')

# List active Zero Trust Tunnels:
cf_security(action='list_tunnels')

6. 범용 REST 게이트웨이 (cf_api)

# Call any specific Cloudflare v4 REST endpoint:
cf_api(method='GET', path='/user')

테스트

pytest tests

라이선스

MIT

A
license - permissive license
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • Connect MCP clients to 2,000+ AI models without managing provider API keys.

  • One PAT, any MCP agent: Vercel, GitHub, Cloudflare, Supabase, GCP — unified dev infra gateway.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Steph-ux/cloudflare-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server