Overview

The Cloudflare MCP Server allows AI models to interact with various Cloudflare services. It's part of the Model Context Protocol (MCP) system, providing a standardized way for LLMs to manage and query Cloudflare resources, automate tasks, and gain insights across application development, security, and performance.

Official Server:

Developed and maintained by Cloudflare

Key Features

🌐

Comprehensive Service Integration

Access a wide range of Cloudflare services, from Workers and DNS to security and analytics.

🗣️

Natural Language Interaction

Use natural language prompts to manage and query your Cloudflare resources.

⚙️

Automated Configuration & Management

Automate tasks like reading configurations, deploying Workers, and managing DNS records.

🛠️

Developer Tooling

Integrate with development workflows for Workers, observability, and debugging.

Available Tools

Quick Reference

Tool	Purpose	Category
`get_documentation`	Get Cloudflare reference info	Information
`deploy_worker`	Deploy Cloudflare Workers	Deployment
`get_logs`	Retrieve Worker logs	Observability
`get_internet_traffic_trends`	Get global internet trends	Analytics
`get_dns_query_logs`	Optimize DNS performance	DNS Management

Detailed Usage

get_documentation▶

Retrieve up-to-date reference information on Cloudflare services.

use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "get_documentation",
  arguments: {
    query: "Cloudflare Workers KV"
  }
});

deploy_worker▶

Deploy a new Cloudflare Worker or update an existing one.

use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "deploy_worker",
  arguments: {
    name: "my-new-worker",
    script: "export default { async fetch(request) { return new Response('Hello Worker!'); } }"
  }
});

get_logs▶

Retrieve logs for a specific Cloudflare Worker.

use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "get_logs",
  arguments: {
    worker_name: "my-worker",
    time_range: "1 hour ago"
  }
});

get_internet_traffic_trends▶

Get global internet traffic insights and trends from Cloudflare Radar.

use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "get_internet_traffic_trends",
  arguments: {
    country: "US"
  }
});

get_dns_query_logs▶

Retrieve DNS query logs to optimize performance and debug issues.

use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "get_dns_query_logs",
  arguments: {
    zone_id: "your-zone-id"
  }
});

Installation

{
  "mcpServers": {
    "cloudflare-observability": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://observability.mcp.cloudflare.com/mcp"
      ]
    },
    "cloudflare-bindings": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://bindings.mcp.cloudflare.com/mcp"
      ]
    }
  }
}

Deploying Your Own Cloudflare MCP Server

You can also deploy your own custom MCP server on Cloudflare Workers.

Create a new Worker project:

npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server

Install dependencies:
```
npm install
```
Start the development server:
```
npm start
```
Your MCP server will be running on http://localhost:8788/sse.
Deploy to Cloudflare:
```
npx wrangler@latest deploy
```

Custom Worker Deployment:

This Docker configuration assumes you have deployed your own Cloudflare Worker MCP server and are providing its URL.

Common Use Cases

1. Automated Infrastructure Management

Manage DNS records, firewall rules, and Workers deployments through natural language:

// Update DNS record
use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "update_dns_record",
  arguments: {
    zone_id: "your-zone-id",
    record_id: "your-record-id",
    type: "A",
    name: "example.com",
    content: "192.0.2.1"
  }
});

2. Observability and Debugging

Query logs, analyze performance metrics, and debug Workers applications using AI agents:

// Get Worker errors
use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "get_logs",
  arguments: {
    worker_name: "my-app-worker",
    log_level: "error",
    time_range: "24 hours"
  }
});

3. Content Delivery Optimization

Configure caching, image optimization, and other CDN settings:

// Purge cache for a URL
use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "purge_cache",
  arguments: {
    zone_id: "your-zone-id",
    url: "https://www.example.com/image.jpg"
  }
});

4. Security Policy Enforcement

Update WAF rules, manage bot protection, and configure access policies:

// Block an IP address
use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "update_waf_rule",
  arguments: {
    zone_id: "your-zone-id",
    rule_id: "your-rule-id",
    action: "block",
    filter: "ip.src eq 1.2.3.4"
  }
});

5. AI-Powered Development

Build and deploy AI applications on Cloudflare Workers, leveraging MCP for seamless integration:

// Deploy an AI Worker
use_mcp_tool({
  server_name: "cloudflare",
  tool_name: "deploy_worker",
  arguments: {
    name: "ai-inference-worker",
    script: "// AI inference logic here"
  }
});

Blockchain and Web3 Development

Integrate AI with blockchain networks and Web3 tooling to manage wallets, execute transactions, call smart contracts, and build decentralized applications across multiple chains.

Filesystem MCP Server

Filesystem MCP servers enable AI models to interact with local file systems, providing capabilities for file operations, directory management, and secure file access within specified boundaries.

MySQL MCP Server

MySQL MCP servers enable AI models to interact with MySQL databases, providing capabilities for structured data operations, SQL queries, transaction management, and relational data management.

Cloudflare MCP Server