| [ Web Proxy ] |
| Viewing: https://developers.cloudflare.com/agent-setup/opencode/ | [Back] [Original] |
Open-source terminal agent with a rich TUI that works with 75+ LLMs. Made by Anomaly.
Install OpenCode
Install OpenCode. For npm, Homebrew, Bun, Scoop, or Windows options, see the OpenCode install guide .
curl -fsSL https://opencode.ai/install | bash
Install Cloudflare Skills
npx skills add https://github.com/cloudflare/skills
Add Cloudflare MCP servers
Add MCP servers to .opencode.jsonc. For domain-specific MCP servers, refer to mcp-server-cloudflare . For the full Cloudflare API MCP server (Code Mode), refer to cloudflare/mcp .
{
"mcp": {
"cloudflare": { "type": "remote", "url": "https://mcp.cloudflare.com/mcp", "enabled": true },
"cloudflare-docs": { "type": "remote", "url": "https://docs.mcp.cloudflare.com/mcp", "enabled": true },
"cloudflare-bindings": { "type": "remote", "url": "https://bindings.mcp.cloudflare.com/mcp", "enabled": true },
"cloudflare-builds": { "type": "remote", "url": "https://builds.mcp.cloudflare.com/mcp", "enabled": true },
"cloudflare-observability": { "type": "remote", "url": "https://observability.mcp.cloudflare.com/mcp", "enabled": true }
}
}
Launch OpenCode
Start OpenCode from the root of your project, where wrangler.jsonc lives (if it already exists).
opencode
Try a prompt
For example:
Add bot protection and rate limiting to my login and checkout endpoints.
Expand any section to learn more.
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.
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.
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.
What’s next
The unified cf CLI is in technical preview — a next-generation CLI that covers every Cloudflare product with consistent verbs and ergonomic output for agents. Try it with npx cf. Read the announcement →
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:
For a full overview of how these docs are structured for agents, refer to the Docs for Agents guide.
Set up custom domains with automatic SSL for my SaaS customers using SSL for SaaS.Create a Logpush job to stream Workers analytics to my data warehouse.Build a multi-tenant SaaS backend where each customer gets an isolated D1 database.Set up rate limiting and WAF rules to block abuse on my public API.Build a serverless AI inference endpoint on Workers AI with streaming responses./cloudflare:build-agent or /cloudflare:build-mcp slash commands.All three. Skills provide persistent Cloudflare expertise so OpenCode knows
when to reach for Durable Objects vs KV, how to structure a Workers project,
and when to call CLI vs API. The Cloudflare API MCP server handles platform
operations (DNS, WAF, Zero Trust, R2 buckets). Wrangler handles local dev,
deploys, and Workers-specific commands. The bundled wrangler Skill teaches
OpenCode which to use.
The first time OpenCode calls a Cloudflare tool, you will be redirected to authorize via OAuth and choose permissions.
Yes. OpenCode supports 75+ model providers, including Cloudflare Workers AI.
Configure your model in .opencode.jsonc.
Yes. OpenCode is fully open source and available at github.com/anomalyco/opencode.
Verify the MCP configuration in .opencode.jsonc uses "type": "remote"
with the correct URL. Run opencode mcp list to check connected servers.
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 moreShip a remote MCP server on Workers with OAuth, durable state, and streamable HTTP transport.
Learn moreRun open-source LLMs, embedding models, and image models at the edge. Use it as your agent's model provider.
Learn moreLoad user-generated code into isolated Workers on demand. The secure sandbox behind Code Mode.
Learn moreTerminal-based coding agent that understands your codebase, runs commands, edits files, and manages git. Made by Anthropic.
View guideOpenAI coding agent available as a terminal CLI and desktop app. It reads and writes files, runs commands, and browses the web in a sandbox.
View guideAI-first IDE built on VS Code with multi-file Composer edits and background agents. Made by Cursor.
View guideEditor extension and CLI with agent mode, workspace context, and native PR integration. Made by GitHub.
View guideAgentic IDE with Cascade context and Flows for multi-step tasks. Made by Cognition.
View guideFree, open-source code editor with native Model Context Protocol (MCP) client support and Copilot Chat integration. Made by Microsoft.
View guideCommand Code is one of the most used coding agents for open models. It automatically learns your coding taste and self-improves as you work.
View guidePowerful agent for coding and work. Natively local, with open models in the cloud. By LM Studio.
View guide| Web Proxy Viewer | New URL | Original Page |