# Wrangler MCP — Cloudflare Workers for AI Agents

> MCP server for managing Cloudflare Workers, KV, R2, and D1 from AI agents. Deploy serverless functions, manage storage, and query databases through Claude Code tool calls.

## Install

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

## Quick Use

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

Now ask your AI agent:
```
"Deploy this Worker script to Cloudflare"
"List all KV namespaces"
"Query the users table in D1"
"Upload this file to R2 bucket"
```

## What is Wrangler MCP?

Wrangler MCP is Cloudflare's official MCP server that gives AI agents access to the Cloudflare developer platform. Manage Workers (serverless functions), KV (key-value store), R2 (object storage), D1 (SQLite database), and more — all through structured MCP tool calls. Deploy, query, and manage cloud infrastructure without leaving your AI coding session.

**Answer-Ready**: Cloudflare's official MCP server for AI agents. Manage Workers, KV, R2, D1, and Queues through tool calls. Deploy serverless functions, query databases, manage storage from Claude Code or Cursor. Official Cloudflare product.

**Best for**: Developers deploying to Cloudflare with AI coding agents. **Works with**: Claude Code, Cursor, Claude Desktop. **Setup time**: Under 3 minutes.

## Core Tools

### Workers (Serverless)

| Tool | What It Does |
|------|-------------|
| worker_list | List all Workers |
| worker_deploy | Deploy a Worker script |
| worker_delete | Remove a Worker |
| worker_get | Get Worker details and code |
| worker_logs | View Worker logs |

### KV (Key-Value Store)

| Tool | What It Does |
|------|-------------|
| kv_list_namespaces | List KV namespaces |
| kv_get | Read a key |
| kv_put | Write a key-value pair |
| kv_delete | Delete a key |
| kv_list_keys | List keys in namespace |

### D1 (SQLite Database)

| Tool | What It Does |
|------|-------------|
| d1_list | List databases |
| d1_query | Execute SQL query |
| d1_create | Create new database |

### R2 (Object Storage)

| Tool | What It Does |
|------|-------------|
| r2_list_buckets | List buckets |
| r2_get_object | Download object |
| r2_put_object | Upload object |
| r2_delete_object | Delete object |

## Use Cases

| Use Case | Example |
|----------|---------|
| Deploy API | "Create a Worker that returns JSON from D1" |
| Data Management | "Query all users created today from D1" |
| File Storage | "Upload build artifacts to R2" |
| Config Management | "Store API config in KV namespace" |
| Edge Functions | "Deploy a rate limiter Worker" |

## FAQ

**Q: Is this the official Cloudflare MCP?**
A: Yes, published by Cloudflare under `@cloudflare/mcp-server-cloudflare`.

**Q: Can it deploy full applications?**
A: It deploys individual Workers. For full Wrangler workflows (wrangler.toml, multi-script), use the Wrangler CLI directly.

**Q: Is it free?**
A: Cloudflare Workers has a free tier (100K requests/day). The MCP server itself is free.

## Source & Thanks

> Created by [Cloudflare](https://github.com/cloudflare). Official MCP server.
>
> [cloudflare/mcp-server-cloudflare](https://github.com/cloudflare/mcp-server-cloudflare)

<!-- ZH -->

## 快速使用

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

让 AI Agent 管理 Cloudflare Workers/KV/R2/D1。

## 什么是 Wrangler MCP？

Cloudflare 官方 MCP 服务器，AI Agent 通过工具调用管理 Workers、KV、R2、D1。

**一句话总结**：Cloudflare 官方 MCP，AI Agent 管理 Workers（Serverless）/KV/R2/D1，部署函数/查询数据库/管理存储，官方出品。

## 核心工具

Workers：部署/列出/删除/日志
KV：读写键值对
D1：SQL 查询
R2：对象存储

## 常见问题

**Q: 官方的？**
A: 是，Cloudflare 发布的 `@cloudflare/mcp-server-cloudflare`。

## 来源与致谢

> [cloudflare/mcp-server-cloudflare](https://github.com/cloudflare/mcp-server-cloudflare) — 官方

---
Source: https://tokrepo.com/en/workflows/70204503-1a90-4c8b-9e87-b36f65798fe7
Author: MCP Hub