Cloudflare AI App Builder
A source-backed Cloudflare collection for building AI apps on the edge: combine Workers, Workers AI, Agents, D1, KV, R2, Wrangler deployment operations, and Cloudflare MCP access with explicit environment and data boundaries.
Open the source and read safety notes before installing.
Safety notes
- This collection runs nothing itself; linked entries can deploy Workers, inspect Cloudflare resources, or change app configuration.
- Use preview/staging environments and scoped API tokens before allowing Claude-assisted deployment or MCP operations.
- Review storage consistency, cache behavior, and rollback plans before moving AI workflows to production traffic.
Privacy notes
- The collection stores no data itself; linked Cloudflare resources may process prompts, user requests, logs, analytics, object storage, or database rows.
- Workers AI and external model calls may involve account-level telemetry and provider-specific retention rules.
- Do not paste production secrets, customer data, or Cloudflare API tokens into transcripts or PR comments.
Prerequisites
- A Cloudflare account, Wrangler authentication, and a target account/project for development or staging.
- Agreement on which resources use Workers AI, Agents, D1, KV, R2, Queues, or external APIs.
- Separate secrets and environment bindings for local, preview, staging, and production deployments.
Schema details
- Install type
- copy
- Troubleshooting
- No
- Items
- 9 entries
- Estimated setup
- 80 minutes
- Difficulty
- advanced
Full copyable content
Start with Workers AI and Cloudflare Agents design, add D1/KV/R2 storage boundaries, then use Wrangler and Cloudflare MCP for deployment and operations.About this resource
What this collection sets up
This bundle is for builders shipping AI applications on Cloudflare's edge platform. It pairs app architecture guidance with deployment operations, storage boundaries, MCP access, and operational checks so Claude can help without blurring the line between preview and production resources.
Layers
1. AI runtime and application shape
- cloudflare-agents-sdk provides the Cloudflare Agents foundation for agentic apps on Workers.
- cloudflare-workers-ai-edge focuses on Workers AI usage, bindings, and edge inference patterns.
2. Durable state and platform boundaries
- cloudflare-workers-d1-kv-r2-capability-pack covers storage tradeoffs for D1, KV, and R2.
- environment-variable-validator helps keep account IDs, tokens, and environment bindings explicit before running deployment workflows.
3. Deploy, operate, and iterate
- wrangler-deployment-operations-capability-pack handles Wrangler planning, deploys, versions, and rollback thinking.
- cloudflare-mcp-server exposes Cloudflare operations through MCP when scoped credentials are approved.
- github-actions-ai-cicd and performance-impact-monitor keep CI and performance feedback in the loop.
- zero-budget-saas-launch-capability-pack helps constrain launch scope and free-tier assumptions for early SaaS experiments.
Suggested order
Start by defining the Workers/Agents runtime and storage boundaries, then set up Wrangler and environment validation, then connect Cloudflare MCP and CI/CD. Keep production tokens out of early experiments and make rollback paths part of the first deployment plan.
Source and references
- Cloudflare Workers documentation: https://developers.cloudflare.com/workers/
- Workers AI documentation: https://developers.cloudflare.com/workers-ai/
- Cloudflare Agents documentation: https://developers.cloudflare.com/agents/
- Wrangler documentation: https://developers.cloudflare.com/workers/wrangler/
Duplicate check
Checked existing collections, upstream collection history, open collection PRs,
and repository content for cloudflare-ai-app-builder, Cloudflare AI app,
Workers AI collection, Cloudflare Agents workflow, and Wrangler deployment
collection. Existing AWS, backend, API, data, and SaaS MCP collections do not
provide a Cloudflare-specific AI app builder bundle around Workers, Agents,
Workers AI, storage primitives, Wrangler, and Cloudflare MCP.
Disclosure
Editorial collection. No paid placement or affiliate link is used.
Source citations
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.