cloudflare-mcp v1.0.0

Universal Model Context Protocol (MCP) server for the complete Cloudflare ecosystem. Replaces 16 fragmented remote MCP endpoints with a single, high-performance local server.

Features (7 Unified Tools)

• cf_dns: Zones, DNS records (A, CNAME, TXT, MX, etc.), CDN cache purging
• cf_compute: Cloudflare Workers, KV Key-Value storage, serverless D1 SQL database execution
• cf_storage: R2 Object Storage buckets, Vectorize vector database queries
• cf_ai: Workers AI inference (Llama, DeepSeek, Embeddings), AI Gateway logs and telemetry
• cf_security: Zero Trust Tunnels (cloudflared), WAF firewall rules, Audit logs
• cf_radar: Radar URL scanner, global traffic/attack analytics, GraphQL queries
• cf_api: Universal REST API gateway (access any of the 2,500+ Cloudflare endpoints directly)

Configuration

Set your Cloudflare API Token in your environment or store it in ~/.secrets/cloudflare-token.txt:

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

Installation in MCP Clients (Claude Desktop, OpenCode, Cursor, Windsurf)

Option 1: Instant via uvx (Recommended)

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

Option 2: Via pip install

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

Then in your MCP config:

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

Option 3: Local Clone (Development)

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

Usage Examples

1. DNS Management

# 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 Database & 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 Object Storage

# 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 Inference

# 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 Scan & Security

# 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. Universal REST Gateway (cf_api)

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

Testing

pytest tests

License

MIT