agents-sdk
cloudflare/skills
Build and debug Cloudflare Agents SDK applications with persistent state, RPC, scheduling, and MCP integration.
What is agents-sdk?
The Agents SDK skill provides comprehensive knowledge and patterns for building agents on Cloudflare Workers using the agents package. Use it when creating, debugging, or reviewing agent applications that need persistent state, callable methods, scheduling, workflows, or chat capabilities.
- Access curated Cloudflare Agents documentation with direct links to API references and guides
- Build agents with persistent SQLite-backed state and client synchronization
- Implement callable RPC methods, scheduling (one-time, recurring, cron), and durable workflows
- Integrate Model Context Protocol (MCP) servers and build MCP handlers
- Create streaming chat agents with message persistence, tools, and server-driven responses
- Handle email routing, webhooks, push notifications, and voice (experimental)
How to install agents-sdk
npx skills add https://github.com/cloudflare/skills --skill agents-sdk- Node.js and npm installed
- Cloudflare Workers account and wrangler CLI
- agents package installed (npm install agents)
- For chat agents: @cloudflare/ai-chat, ai, and @ai-sdk/react packages
How to use agents-sdk
- 1.Verify agents package is installed with npm ls agents
- 2.Configure wrangler.jsonc with compatibility_flags, durable_objects bindings, and migrations
- 3.Define your Agent class extending Agent<Env, State> with initialState and validateStateChange
- 4.Implement agent methods using @callable() decorator for RPC or schedule() for background tasks
- 5.For chat agents, use AIChatAgent with streaming, tools, and message persistence
- 6.Test locally with wrangler dev and deploy with wrangler deploy
- 7.Monitor with diagnostics-channel events and check observability documentation for debugging
Use cases
- Building a persistent chatbot with state management and tool integration on Cloudflare Workers
- Creating a background job scheduler with durable execution that survives worker eviction
- Implementing an email-handling agent that receives, processes, and replies to messages
- Setting up a multi-step workflow with human-in-the-loop approvals and retries
- Connecting an agent to external MCP servers for extended capabilities
- Cloudflare Workers developers building agent applications
- Full-stack engineers implementing AI-powered automation
- Backend developers needing durable, persistent background processing
- Teams integrating Model Context Protocol into their infrastructure
agents-sdk FAQ
Always prefer retrieval over pre-training for Agents SDK tasks. The SDK evolves rapidly and the skill provides curated links to current documentation.
No—do NOT enable experimentalDecorators; it breaks the @callable decorator. The agents package handles decorators correctly without this flag.
Use setState() to sync SQLite-backed state to clients, and implement validateStateChange() to enforce state rules. State is automatically persisted in the Durable Object.
schedule() and scheduleEvery() run one-off or recurring tasks; AgentWorkflow is for multi-step durable background processing that survives DO eviction via runFiber() and stash().
Yes—use the MCP client API to connect to external MCP servers, or build your own MCP server with createMcpHandler and secure it with OAuth or a proxy.
Full instructions (SKILL.md)
Source of truth, from cloudflare/skills.
name: agents-sdk description: Build, debug, or review Cloudflare Agents SDK applications using the agents package.
Cloudflare Agents SDK
Your knowledge of the Agents SDK may be outdated. Prefer retrieval over pre-training for any Agents SDK task.
Retrieval Sources
Cloudflare docs: https://developers.cloudflare.com/agents/
| Topic | Docs URL | Use for |
|---|---|---|
| Getting started | Quick start | First agent, project setup |
| Adding to existing project | Add to existing project | Install into existing Workers app |
| Configuration | Configuration | wrangler.jsonc, bindings, assets, deployment |
| Agent class | Agents API | Agent lifecycle, patterns, pitfalls |
| State | Store and sync state | setState, validateStateChange, persistence |
| Routing | Routing | URL patterns, routeAgentRequest |
| Callable methods | Callable methods | @callable, RPC, streaming, timeouts |
| Scheduling | Schedule tasks | schedule(), scheduleEvery(), cron |
| Workflows | Run workflows | AgentWorkflow, durable multi-step tasks |
| HTTP/WebSockets | WebSockets | Lifecycle hooks, hibernation |
| Chat agents | Chat agents | AIChatAgent, streaming, tools, persistence |
| Client SDK | Client SDK | useAgent, AgentClient, state, RPC, HTTP |
| Client tools | Client tools | Client-side tools, autoContinueAfterToolResult |
| Server-driven messages | Autonomous responses | saveMessages, waitUntilStable, server-initiated turns |
| Resumable streaming | Chat agents | Stream recovery on disconnect |
| Email routing, secure reply resolver | ||
| MCP client | MCP client | Connecting to MCP servers |
| MCP server | MCP server | Building MCP servers with createMcpHandler |
| MCP transports | MCP transports | Streamable HTTP, SSE, RPC transport options |
| Securing MCP servers | Securing MCP | OAuth, proxy MCP, hardening |
| Human-in-the-loop | Human-in-the-loop | Workflow approvals, elicitation, timeout handling |
| Durable execution | Durable execution | runFiber(), stash(), surviving DO eviction |
| Queue | Queue | Built-in FIFO queue, queue() |
| Retries | Retries | this.retry(), backoff/jitter |
| Observability | Observability | Diagnostics-channel events |
| Push notifications | Push notifications | Web Push + VAPID from agents |
| Webhooks | Webhooks | Receiving external webhooks |
| Cross-domain auth | Cross-domain auth | WebSocket auth, tokens, CORS |
| Readonly connections | Readonly | shouldConnectionBeReadonly |
| Voice | Voice | Experimental STT/TTS, withVoice |
| Browse the web | Browser tools | Experimental CDP browser automation |
| Think | Think | Experimental higher-level chat agent class |
| Migrations | AI SDK v5, AI SDK v6 | Upgrading @cloudflare/ai-chat |
Capabilities
The Agents SDK provides:
- Persistent state — SQLite-backed, auto-synced to clients via
setState - Callable RPC —
@callable()methods invoked over WebSocket - Scheduling — One-time, recurring (
scheduleEvery), and cron tasks - Workflows — Durable multi-step background processing via
AgentWorkflow - Durable execution —
runFiber()/stash()for work that survives DO eviction - Queue — Built-in FIFO queue with retries via
queue() - Retries —
this.retry()with exponential backoff and jitter - MCP integration — Connect to MCP servers or build your own with
createMcpHandler - Email handling — Receive and reply to emails with secure routing
- Streaming chat —
AIChatAgentwith resumable streams, message persistence, tools - Server-driven messages —
saveMessages,waitUntilStablefor proactive agent turns - React hooks —
useAgent,useAgentChatfor client apps - Observability —
diagnostics_channelevents for state, RPC, schedule, lifecycle - Push notifications — Web Push + VAPID delivery from agents
- Webhooks — Receive and verify external webhooks
- Voice (experimental) — STT/TTS via
@cloudflare/voice - Browser tools (experimental) — CDP-powered browsing via
agents/browser - Think (experimental) — Higher-level chat agent via
@cloudflare/think
FIRST: Verify Installation
npm ls agents # Should show agents package
If not installed:
npm install agents
For chat agents:
npm install agents @cloudflare/ai-chat ai @ai-sdk/react
Wrangler Configuration
{
"compatibility_flags": ["nodejs_compat"],
"durable_objects": {
"bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
},
"migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}
Gotchas:
- Do NOT enable
experimentalDecoratorsin tsconfig (breaks@callable) - Never edit old migrations — always add new tags
- Each agent class needs its own DO binding + migration entry
- Add
"ai": { "binding": "AI" }for Workers AI
Agent Class
import { Agent, routeAgentRequest, callable } from "agents";
type State = { count: number };
export class Counter extends Agent<Env, State> {
initialState = { count: 0 };
validateStateChange(nextState: State, source: Connection | "server") {
if (nextState.count < 0) throw new Error("Count cannot be negative");
}
onStateUpdate(state: State, source: Connection | "server") {
console.log("State updated:", state);
}
@callable()
increment() {
this.setState({ count: this.state.count + 1 });
return this.state.count;
}
}
export default {
fetch: (req, env) => routeAgentRequest(req, env) ?? new Response("Not found", { status: 404 })
};
Routing
Requests route to /agents/{agent-name}/{instance-name}:
| Class | URL |
|---|---|
Counter | /agents/counter/user-123 |
ChatRoom | /agents/chat-room/lobby |
Client: useAgent({ agent: "Counter", name: "user-123" })
Custom routing: use getAgentByName(env.MyAgent, "instance-id") then agent.fetch(request).
Core APIs
| Task | API |
|---|---|
| Read state | this.state.count |
| Write state | this.setState({ count: 1 }) |
| SQL query | this.sql`SELECT * FROM users WHERE id = ${id}` |
| Schedule (delay) | await this.schedule(60, "task", payload) |
| Schedule (cron) | await this.schedule("0 * * * *", "task", payload) |
| Schedule (interval) | await this.scheduleEvery(30, "poll") |
| RPC method | @callable() myMethod() { ... } |
| Streaming RPC | @callable({ streaming: true }) stream(res) { ... } |
| Start workflow | await this.runWorkflow("ProcessingWorkflow", params) |
| Durable fiber | await this.runFiber("name", async (ctx) => { ... }) |
| Enqueue work | this.queue("handler", payload) |
| Retry with backoff | await this.retry(fn, { maxAttempts: 5 }) |
| Broadcast to clients | this.broadcast(message) |
| Get connections | this.getConnections(tag?) |
React Client
Read client-sdk.md for client selection and current connection examples. For chat UI and tools, also read streaming-chat.md.
References
Core
- references/state-scheduling.md — State persistence, scheduling, SQL
- references/callable.md — RPC methods, streaming, timeouts
- references/routing.md — URL patterns, custom routing,
getAgentByName - references/configuration.md — Wrangler config, bindings, Vite setup
Chat & Streaming
- references/streaming-chat.md — AIChatAgent, resumable streams, tools
- references/client-sdk.md —
useAgent,useAgentChat,AgentClient - references/server-driven-messages.md — Trigger patterns,
saveMessages - references/human-in-the-loop.md — Approval flows,
needsApproval
Background Processing
- references/workflows.md — Durable Workflows integration
- references/durable-execution.md —
runFiber,stash, surviving eviction - references/queue-retries.md — Built-in queue, retry with backoff
Integrations
- references/mcp.md — MCP client and server, transports, securing
- references/email.md — Email routing and handling
- references/webhooks-push.md — Webhooks, push notifications
- references/observability.md — Diagnostics-channel events
Experimental
- references/think.md —
@cloudflare/thinkhigher-level chat agent - references/voice.md —
@cloudflare/voiceSTT/TTS - references/codemode.md — Code Mode for tool orchestration
- references/browse-the-web.md — CDP browser tools
Related skills
More from cloudflare/skills and the wider catalog.

building-ai-agent-on-cloudflare
Build stateful AI agents on Cloudflare Workers with WebSockets, state persistence, and scheduled tasks.

building-mcp-server-on-cloudflare
Build and deploy remote MCP servers on Cloudflare Workers with tools, OAuth, and production-ready configuration.

cloudflare
Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security.

cloudflare-email-service
Send and route emails through Cloudflare Workers and REST API with built-in domain verification and deliverability controls.

cloudflare-one
Design, configure, and troubleshoot Cloudflare One Zero Trust and SASE deployments.

cloudflare-one-migrations
Assess and plan migrations from VPN, SWG, or SASE platforms to Cloudflare One with policy mapping and rollout strategy.