Claude Code + Cloudflare
AnthropicTerminal-based coding agent that understands your codebase, runs commands, edits files, and manages git. Made by Anthropic.
-
Install Claude Code
Install the Claude Code CLI. For Windows, Homebrew, WinGet, or npm, see the Claude Code setup guide ↗.
curl -fsSL https://claude.ai/install.sh | bash -
Launch Claude Code in your project
Start Claude Code from the root of your project, where
wrangler.jsonclives (if it already exists).claude -
Install the Cloudflare plugin
In Claude Code, run these two slash commands. This installs Cloudflare Skills and registers the Cloudflare MCP servers.
/plugin marketplace add cloudflare/skills /plugin install cloudflare@cloudflare -
Try a prompt
For example:
Add a D1 database to my Worker and create a users table with full CRUD endpoints.
Expand any section to learn more.
Cloudflare Skills
Persistent platform context that teaches the agent how Cloudflare works.
Skills are instructions the agent loads on demand. The cloudflare/skills bundle covers every layer of the platform — so the agent knows your conventions without you re-explaining them.
MCP servers
Live access to the Cloudflare API, docs, and observability.
MCP servers provide typed tools to call into Cloudflare at runtime. There are two options: Code Mode — a single server that covers the entire Cloudflare API (2,500+ endpoints in ~1,000 tokens) — or a set of focused, domain-specific servers hosted in the cloudflare/mcp-server-cloudflare repo. The full catalog is also in the MCP servers for Cloudflare docs.
Wrangler CLI
Local dev, deploys, and Workers-specific commands.
Use Wrangler for local development, deploys,
and product-specific commands like wrangler d1 migrations apply or wrangler tail.
The bundled wrangler Skill teaches the agent when to reach
for it.
Agent-friendly docs
Token-efficient references optimized for agents.
Append /index.md to any Cloudflare docs URL for a clean markdown
version. Every top-level product section also has its own llms.txt — a page index sized for a single context window. A few
useful ones:
- developers.cloudflare.com/llms.txt — directory of every Cloudflare product.
- developers.cloudflare.com/workers/llms.txt
- developers.cloudflare.com/agents/llms.txt
- developers.cloudflare.com/r2/llms.txt
- developers.cloudflare.com/d1/llms.txt
For a full overview of how these docs are structured for agents, refer to the Docs for Agents guide.
- The Skills plugin includes a wrangler Skill — Claude knows when to reach for
npx wrangler deploy,wrangler d1 migrations apply, and other CLI commands automatically. - Try the
/cloudflare:build-agentslash command to scaffold a complete Agents SDK project, or/cloudflare:build-mcpfor a remote MCP server. - The Cloudflare API MCP server uses Code Mode — Claude writes JavaScript against a TypeScript API to hit any of 2,500+ endpoints in ~1,000 tokens.
- Claude Code works best from the root of your Workers project where
wrangler.jsonclives — this is what the agent uses to understand your bindings. - Use
claude mcp listto verify Cloudflare servers are connected. For CI/CD, skip OAuth by passing a Cloudflare API token as a bearer token instead. - For more information on installing additional MCP servers, or when to use Code Mode versus traditional MCP servers, refer to the Cloudflare MCP server repository ↗.
Should I use Skills, the MCP server, Wrangler CLI, or all of them?
All three — and the Skills plugin configures them together. Skills give
Claude persistent Cloudflare knowledge (when to use Durable Objects vs KV,
what a good Workers project layout looks like). The Cloudflare API MCP
server handles platform operations (DNS, WAF, R2 buckets, Zero Trust).
Wrangler runs local dev and Workers-specific commands. The wrangler Skill
teaches Claude when to reach for which.
How do I give Claude Code access to my Cloudflare account?
The first time Claude calls a Cloudflare tool, you will be redirected to authorize via OAuth and choose what permissions to grant.
Can Claude Code deploy to existing Workers projects?
Yes. Run Claude Code from your existing project directory where
wrangler.jsonc is located, and it will understand your project
configuration and deploy accordingly.
What does Code Mode mean for MCP?
Code Mode is how the Cloudflare API MCP server fits all 2,500+ API endpoints
into ~1,000 tokens. Instead of exposing every endpoint as a separate tool,
it exposes two — search() and execute() — and Claude writes JavaScript
to call them. Learn more about Code Mode ↗.
MCP server connection fails or times out
Run claude mcp list to verify the server is registered. Try removing and
re-adding: claude mcp remove cloudflare then re-add it. Ensure you have
npx and mcp-remote available.
Claude cannot authenticate with Cloudflare
The MCP server uses OAuth. When prompted, complete the authorization flow in your browser. For CI/CD, create a Cloudflare API token and pass it as a bearer token instead.
Getting outdated information about Cloudflare products
Enable the Cloudflare docs MCP server so the agent can fetch
current documentation at runtime. If you prefer not to use the MCP server, point
the agent directly at developers.cloudflare.com/llms.txt for
a directory of every product, or developers.cloudflare.com/<product>/llms.txt
for a product-specific index.
Cloudflare is not just a deploy target for agents, it is a full stack for building your own.
Stateful AI agents with state, scheduling, RPC, email, streaming chat — and the Code Mode SDK for token-efficient tool use.
Learn more →Ship a remote MCP server on Workers with OAuth, durable state, and streamable HTTP transport.
Learn more →Run open-source LLMs, embedding models, and image models at the edge. Use it as your agent's model provider.
Learn more →Load user-generated code into isolated Workers on demand. The secure sandbox behind Code Mode.
Learn more →
Lightweight open-source terminal agent that reads and writes files, runs commands, and browses the web in a sandbox. Made by OpenAI.
AI-first IDE built on VS Code with multi-file Composer edits and background agents. Made by Cursor.
Editor extension and CLI with agent mode, workspace context, and native PR integration. Made by GitHub.
Open-source terminal agent with a rich TUI that works with 75+ LLMs. Made by Anomaly.
Agentic IDE with Cascade context and Flows for multi-step tasks. Made by Cognition.