Skip to main content
Glama
deenesjakoruzh
Steph-ux

cloudflare-mcp

by Steph-ux
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

cloudflare-mcp v1.0.0

面向完整 Cloudflare 生态系统的通用 Model Context Protocol (MCP) 服务器。 用一个高性能的本地服务器取代 16 个分散的远程 MCP 端点。

功能（7 个统一工具）

  • cf_dns：区域、DNS 记录（A、CNAME、TXT、MX 等）、CDN 缓存清除

  • cf_compute：Cloudflare Workers、KV 键值存储、无服务器 D1 SQL 数据库执行

  • cf_storage：R2 对象存储桶、Vectorize 向量数据库查询

  • cf_ai：Workers AI 推理（Llama、DeepSeek、Embeddings）、AI Gateway 日志和遥测

  • cf_security：Zero Trust 隧道（cloudflared）、WAF 防火墙规则、审计日志

  • cf_radar：Radar URL 扫描器、全球流量/攻击分析、GraphQL 查询

  • cf_api：通用 REST API 网关（直接访问 2,500+ 个 Cloudflare 端点）

Related MCP server: mcp-server-cloudflare

配置

在您的环境中设置 Cloudflare API Token，或将其存储在 ~/.secrets/cloudflare-token.txt 中：

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

在 MCP 客户端中安装（Claude Desktop、OpenCode、Cursor、Windsurf）

选项 1：通过 uvx 即时安装（推荐）

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

选项 2：通过 pip install 安装

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

然后在您的 MCP 配置中：

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

选项 3：本地克隆（开发）

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

使用示例

1. DNS 管理

# 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 数据库与 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 对象存储

# 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 推理

# 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 扫描与安全

# 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. 通用 REST 网关（cf_api）

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

测试

pytest tests

许可证

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers