# Cloudflare Workers MCP — Edge Functions for AI Agents

> MCP server that gives AI agents access to Cloudflare Workers for deploying edge functions, managing KV storage, R2 buckets, and D1 databases. Build and deploy serverless code from chat. 1,500+ stars.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

Add to your `.mcp.json`:

```json
{
  "mcpServers": {
    "cloudflare": {
      "command": "npx",
      "args": ["-y", "@cloudflare/mcp-server-cloudflare"],
      "env": {
        "CLOUDFLARE_API_TOKEN": "your-token"
      }
    }
  }
}
```

Get your token at [dash.cloudflare.com/profile/api-tokens](https://dash.cloudflare.com/profile/api-tokens). Restart Claude Code.

---

## Intro

Cloudflare Workers MCP is a Model Context Protocol server that connects AI agents to the Cloudflare developer platform with 1,500+ GitHub stars. Deploy edge functions, manage KV key-value storage, R2 object storage, and D1 SQLite databases — all through natural language commands. Your AI agent can write, deploy, and manage serverless infrastructure without leaving the conversation. Best for developers using Cloudflare who want AI-assisted edge deployment. Works with: Claude Code, Cursor, any MCP client. Setup time: under 2 minutes.

---

## Available Tools

### Workers
```
"Deploy a new worker that returns the current time in JSON"
"List all my deployed workers"
"Show the code of my auth-worker"
"Delete the old-api worker"
```

### KV Storage
```
"Store user preferences in KV namespace 'settings'"
"Read the value for key 'config:feature-flags'"
"List all keys in the 'cache' namespace"
```

### R2 Object Storage
```
"Upload this file to the 'assets' R2 bucket"
"List all objects in the 'backups' bucket"
"Generate a presigned URL for report.pdf"
```

### D1 Database
```
"Create a D1 database called 'app-data'"
"Run this SQL: CREATE TABLE users (id INTEGER PRIMARY KEY, name TEXT)"
"Query: SELECT * FROM users WHERE created_at > date('now', '-7 days')"
```

## Use Cases

### Instant API Deployment
```
"Write a worker that proxies requests to our internal API with rate limiting, then deploy it"
-> Agent writes the code, deploys to Cloudflare edge, returns the URL
```

### Edge Data Management
```
"Store our feature flags in KV and create a worker endpoint to serve them"
-> Agent creates KV entries and a worker that reads them
```

### Key Stats
- 1,500+ GitHub stars
- Workers, KV, R2, D1 access
- Deploy from conversation
- 300+ edge locations globally
- Official Cloudflare product

### FAQ

**Q: What is Cloudflare Workers MCP?**
A: An MCP server that gives AI agents access to Cloudflare Workers, KV, R2, and D1 for deploying and managing edge infrastructure via natural language.

**Q: Is it free?**
A: The MCP server is open-source. Cloudflare Workers free tier includes 100K requests/day.

**Q: Can the agent deploy to production?**
A: Yes, use separate API tokens with limited permissions for safety.

---

## Source & Thanks

> Created by [Cloudflare](https://github.com/cloudflare). Licensed under MIT.
>
> [mcp-server-cloudflare](https://github.com/cloudflare/mcp-server-cloudflare) — stars 1,500+

---

<!-- ZH -->


## Quick Start

Add to `.mcp.json`:

```json
{
  "mcpServers": {
    "cloudflare": {
      "command": "npx",
      "args": ["-y", "@cloudflare/mcp-server-cloudflare"],
      "env": { "CLOUDFLARE_API_TOKEN": "your-token" }
    }
  }
}
```

---

## Overview

Cloudflare Workers MCP is the MCP server for Cloudflare's developer platform with 1,500+ GitHub stars. AI agents can deploy edge functions, manage KV storage, R2 object storage, and D1 databases. Best for developers using Cloudflare.

---

## Source & Thanks

> Created by [Cloudflare](https://github.com/cloudflare). Licensed under MIT.

---
Source: https://tokrepo.com/en/workflows/cloudflare-workers-mcp-edge-functions-ai-agents-d0283053
Author: Cloudflare