cloudflare▌

Durable, long-running workflows with automatic retries, state persistence, and event handling on Cloudflare Workers. \n \n Supports three core step types: step.do() for work execution with configurable retries, step.sleep() for delays, and step.waitForEvent() for external event handling with timeouts \n Automatically persists serializable state across steps and hibernation; prevents 12 documented errors including waitForEvent timeout bugs, I/O context violations, and non-idempotent operation pit

OAuth authentication for MCP servers on Cloudflare Workers with Google Sign-In and Dynamic Client Registration. \n \n Implements dual OAuth role pattern: MCP server acts as both OAuth client (to Google) and OAuth server (to MCP clients like Claude.ai), issuing its own tokens after upstream authentication \n Includes production-ready security: CSRF protection via HttpOnly cookies, one-time-use state tokens with 10-minute TTL, session binding via SHA-256 hashing, and HMAC-signed approval cookies t

Run LLMs, embeddings, and image generation on Cloudflare's GPU network with 14 new 2025 models, streaming support, and 7 documented error preventions. \n \n Supports 40+ models across text generation (Llama 4, Gemma 3, Mistral 3.1, GPT-OSS), embeddings (BGE 2x faster, EmbeddingGemma), image generation (Flux, Leonardo), vision, and audio (Deepgram, Whisper v3) \n Handles critical 2025 breaking changes: context window validation switched from characters to tokens, BGE pooling parameter no longer b

Build Python serverless APIs on Cloudflare Workers with async-only execution, external package support, and multi-step workflow automation. \n \n Deploy Python APIs using the WorkerEntrypoint class pattern with pywrangler CLI; supports all Cloudflare bindings (D1, KV, R2, Workers AI, Durable Objects, Queues) \n Requires async-only code: use httpx or aiohttp for HTTP calls, avoid sync libraries like requests and native C extensions \n Python Workflows enable durable multi-step DAG automation with

Stateful Durable Objects for real-time apps, coordination, and persistent state management. \n \n SQLite-backed storage with 10GB capacity, SQL queries, and atomic transactions; KV backend available for simpler key-value use cases \n WebSocket hibernation API supports thousands of concurrent connections with automatic wake-up; message size limit increased to 32 MiB (Oct 2025) \n Alarms API for scheduling future tasks, batching, and cleanup without relying on setTimeout / setInterval \n RPC metho

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and platform services. \n \n Covers 40+ Cloudflare products organized by use case: compute (Workers, Pages, Durable Objects, Workflows), storage (KV, D1, R2, Queues), AI/ML (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), and security (WAF, Bot Management, Turnstile) \n Includes decision trees to route users to the right product based on their need (run code, store data, add AI, networking, security, or

Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references.

Hit the Cloudflare REST API directly when wrangler CLI or MCP servers aren't the right tool. For bulk operations, fleet-wide changes, and features that wrangler doesn't expose.

Investigate with evidence, not assumptions. Always query Cloudflare API to examine actual configuration before diagnosing issues. The skill's value is the systematic investigation methodology, not predetermined solutions.

Hono was originally built for Cloudflare Workers and provides first-class support for the entire Cloudflare ecosystem including KV, D1, R2, Durable Objects, Queues, and more.