building-mcp-server-on-cloudflare — Claude skill: MCP servers
A skill that walks the agent through building a remote MCP server on Cloudflare Workers: tools, OAuth, deployment. Useful when you need to expose your own functions over MCP.
npx skills add openai/plugins --skill building-mcp-server-on-cloudflare -a codexWhat building-mcp-server-on-cloudflare does
The skill kicks in when you ask to build an MCP server, add OAuth, or deploy one to Workers. Inside is a step-by-step path: define tools with server.tool(), wire up the entry point, test locally in MCP Inspector, ship with npx wrangler deploy, then connect a client via codex mcp add.
Input validation runs on Zod — types, enums, ranges. A separate section covers bindings like D1 and KV through this.env, plus a minimal wrangler.toml with durable objects and migrations. For authenticated servers the skill points to references/oauth-setup.md, listing GitHub, Google, Auth0, Stytch, WorkOS and any OAuth 2.0 provider.
You need a Cloudflare account with Workers enabled, Node.js 18+ and the Wrangler CLI. The skill deliberately biases the agent toward reading Cloudflare docs and the MCP spec instead of pre-trained knowledge — SDK details go stale, so trusting memory here is a bad bet.
What it helps with
- build a remote MCP server on Cloudflare Workers
- define MCP tools with Zod-validated parameters
- attach an OAuth provider to an MCP server
- deploy the Worker and register it as an MCP client in Claude
- debug connection failures and OAuth redirect errors
Example prompts for the agent
- build an MCP server on Cloudflare Workers with a weather tool
- add GitHub OAuth to my MCP server
- deploy my MCP server to Workers and connect it in Claude
How to install building-mcp-server-on-cloudflare
1Skills CLI (Vercel)
npx skills add openai/plugins --skill building-mcp-server-on-cloudflare -a codex2Manually: put the files in place
.agents/skills/building-mcp-server-on-cloudflare/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill building-mcp-server-on-cloudflare -a claude-code2Manually: put the files in place
~/.claude/skills/building-mcp-server-on-cloudflare/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/building-mcp-server-on-cloudflare/
Manually: put the files in place
.cursor/skills/building-mcp-server-on-cloudflare/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins building-mcp-server-on-cloudflare2Manually: put the files in place
.github/skills/building-mcp-server-on-cloudflare/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/cloudflare/skills/building-mcp-server-on-cloudflareManually: put the files in place
.devin/skills/building-mcp-server-on-cloudflare/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them
Questions about building-mcp-server-on-cloudflare
How do I install building-mcp-server-on-cloudflare in Claude?
Run npx skills add openai/plugins --skill building-mcp-server-on-cloudflare, then npx skills add openai/plugins --skill building-mcp-server-on-cloudflare -a codex. The skill then lives at .agents/skills/building-mcp-server-on-cloudflare/SKILL.md.
What does building-mcp-server-on-cloudflare do?
It guides you through building a remote MCP server on Cloudflare Workers: generating tool code, configuring an OAuth provider, testing locally and deploying. It pulls current Cloudflare docs rather than relying on pre-trained knowledge.
What do I need before using this skill?
A Cloudflare account with Workers enabled, Node.js 18+ and the Wrangler CLI, installed with npm install -g wrangler. Authenticated servers also need an OAuth app configured.
Source text
SKILL.md · MIT
---
name: building-mcp-server-on-cloudflare
description: |
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers
with tools, OAuth authentication, and production deployment. Generates
server code, configures auth providers, and deploys to Workers.
Use when: user wants to "build MCP server", "create MCP tools", "remote
MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol
on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment".
Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
---
# Building MCP Servers on Cloudflare
Your knowledge of the MCP SDK and Cloudflare Workers integration may be outdated. **Prefer retrieval over pre-training** for any MCP server task.
## Retrieval Sources
| Source | How to retrieve | Use for |
|--------|----------------|---------|
| MCP docs | `https://developers.cloudflare.com/agents/mcp/` | Server setup, auth, deployment |
| MCP spec | `https://modelcontextprotocol.io/` | Protocol spec, tool/resource definitions |
| Workers docs | Search tool or `https://developers.cloudflare.com/workers/` | Runtime APIs, bindings, config |
## When to Use
- User wants to build a remote MCP server
- User needs to expose tools via MCP
- User asks about MCP authentication or OAuth
- User wants to deploy MCP to Cloudflare Workers
## Prerequisites
- Cloudflare account with Workers enabled
- Node.js 18+ and npm/pnpm/yarn
- Wrangler CLI (`npm install -g wrangler`)
## Quick Start
### Option 1: Public Server (No Auth)
```bash
npm create cloudflare@latest -- my-mcp-server \
--template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server
npm start
```
Server runs at `http://localhost:8788/mcp`
### Option 2: Authenticated Server (OAuth)
```bash
npm create cloudflare@latest -- my-mcp-server \
--template=cloudflare/ai/demos/remote-mcp-github-oauth
cd my-mcp-server
```
Requires OAuth app setup. See [references/oauth-setup.md](references/oauth-setup.md).
## Core Workflow
### Step 1: Define Tools
Tools are functions MCP clients can call. Define them using `server.tool()`:
```typescript
import { McpAgent } from "agents/mcp";
import { z } from "zod";
export class MyMCP extends McpAgent {
server = new Server({ name: "my-mcp", version: "1.0.0" });
async init() {
// Simple tool with parameters
this.server.tool(
"add",
{ a: z.number(), b: z.number() },
async ({ a, b }) => ({
content: [{ type: "text", text: String(a + b) }],
})
);
// Tool that calls external API
this.server.tool(
"get_weather",
{ city: z.string() },
async ({ city }) => {
const response = await fetch(`https://api.weather.com/${city}`);
const data = await response.json();
return {
content: [{ type: "text", text: JSON.stringify(data) }],
};
}
);
}
}
```
### Step 2: Configure Entry Point
**Public server** (`src/index.ts`):
```typescript
import { MyMCP } from "./mcp";
export default {
fetch(request: Request, env: Env, ctx: ExecutionContext) {
const url = new URL(request.url);
if (url.pathname === "/mcp") {
return MyMCP.serveSSE("/mcp").fetch(request, env, ctx);
}
return new Response("MCP Server", { status: 200 });
},
};
export { MyMCP };
```
**Authenticated server** — See [references/oauth-setup.md](references/oauth-setup.md).
### Step 3: Test Locally
```bash
# Start server
npm start
# In another terminal, test with MCP Inspector
npx @modelcontextprotocol/inspector@latest
# Open http://localhost:5173, enter http://localhost:8788/mcp
```
### Step 4: Deploy
```bash
npx wrangler deploy
```
Server accessible at `https://[worker-name].[account].workers.dev/mcp`
### Step 5: Connect Clients
**Codex MCP client setup:**
```bash
codex mcp add my-server -- npx mcp-remote https://my-mcp.workers.dev/mcp
```
Restart Codex after updating the MCP configuration.
## Tool Patterns
### Return Types
```typescript
// Text response
return { content: [{ type: "text", text: "result" }] };
// Multiple content items
return {
content: [
{ type: "text", text: "Here's the data:" },
{ type: "text", text: JSON.stringify(data, null, 2) },
],
};
```
### Input Validation with Zod
```typescript
this.server.tool(
"create_user",
{
email: z.string().email(),
name: z.string().min(1).max(100),
role: z.enum(["admin", "user", "guest"]),
age: z.number().int().min(0).optional(),
},
async (params) => {
// params are fully typed and validated
}
);
```
### Accessing Environment/Bindings
```typescript
export class MyMCP extends McpAgent<Env> {
async init() {
this.server.tool("query_db", { sql: z.string() }, async ({ sql }) => {
// Access D1 binding
const result = await this.env.DB.prepare(sql).all();
return { content: [{ type: "text", text: JSON.stringify(result) }] };
});
}
}
```
## Authentication
For OAuth-protected servers, see [references/oauth-setup.md](references/oauth-setup.md).
Supported providers:
- GitHub
- Google
- Auth0
- Stytch
- WorkOS
- Any OAuth 2.0 compliant provider
## Wrangler Configuration
Minimal `wrangler.toml`:
```toml
name = "my-mcp-server"
main = "src/index.ts"
compatibility_date = "2024-12-01"
[durable_objects]
bindings = [{ name = "MCP", class_name = "MyMCP" }]
[[migrations]]
tag = "v1"
new_classes = ["MyMCP"]
```
With bindings (D1, KV, etc.):
```toml
[[d1_databases]]
binding = "DB"
database_name = "my-db"
database_id = "xxx"
[[kv_namespaces]]
binding = "KV"
id = "xxx"
```
## Common Issues
### "Tool not found" in Client
1. Verify tool name matches exactly (case-sensitive)
2. Ensure `init()` registers tools before connections
3. Check server logs: `wrangler tail`
### Connection Fails
1. Confirm endpoint path is `/mcp`
2. Check CORS if browser-based client
3. Verify Worker is deployed: `wrangler deployments list`
### OAuth Redirect Errors
1. Callback URL must match OAuth app config exactly
2. Check `GITHUB_CLIENT_ID` and `GITHUB_CLIENT_SECRET` are set
3. For local dev, use `http://localhost:8788/callback`
## References
- [references/examples.md](references/examples.md) — Official templates and production examples
- [references/oauth-setup.md](references/oauth-setup.md) — OAuth provider configuration
- [references/troubleshooting.md](references/troubleshooting.md) — Error codes and fixes
© Cloudflare · MIT · openai/plugins