### Pages Functions - Get Started

Source: https://developers.cloudflare.com/llms.txt

Guides on how to get started with Pages Functions, including setup and basic usage.

```APIDOC
## Getting Started with Pages Functions

### Description
This guide provides the fundamental steps to begin using Pages Functions in your Cloudflare Pages projects.

### Method
N/A (This is a guide, not an executable endpoint)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A

For detailed instructions, please consult the Cloudflare Pages documentation on getting started with Functions.
```

--------------------------------

### Hono Basic Setup and Route

Source: https://hono.dev/

This snippet demonstrates the basic setup of a Hono application and defines a simple GET route that returns a 'Hello Hono!' text response. It imports the Hono class and creates an app instance. This is a fundamental example for starting with Hono.

```javascript
import { Hono } from 'hono'

const app = new Hono()

app.get('/', (c) => c.text('Hello Hono!'))

export default app
```

--------------------------------

### Install and Start MCP Server using npm

Source: https://github.com/cloudflare/ai/tree/main/demos/mcp-client

This snippet shows how to install project dependencies and start the MCP server using npm. It's a common setup for Node.js projects. Ensure you have Node.js and npm installed before running these commands.

```shell
npm install
npm start
```

--------------------------------

### Start Server Setup in Node.js

Source: https://github.com/modelcontextprotocol/typescript-sdk

This JavaScript code snippet demonstrates how to start a server using a setup function. It defines the port and uses a .then() block to handle the server's listening process. If an error occurs during startup, it logs the error to the console. This is a standard pattern for initializing and running Node.js servers.

```javascript
// Start the server
const PORT = 3000;
setupServer().then(() => {
 app.listen(PORT, (error) => {
  if (error) {
   console.error(
```

--------------------------------

### Realtime Agents API - Getting Started

Source: https://developers.cloudflare.com/llms.txt

This section provides guidance on deploying your first Realtime Agent using the CLI.

```APIDOC
## Realtime Agents API - Getting Started

### Description
Deploy your first Realtime Agent using the CLI.

### Method
Not specified (CLI-based)

### Endpoint
Not applicable (CLI-based)

### Parameters

#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
```bash
# Example CLI command (specific command not provided in source text)
cloudflare-cli realtime-agents deploy --agent-name my-first-agent
```

### Response
#### Success Response
Deployment status and confirmation.

#### Response Example
```json
{
  "status": "success",
  "message": "Realtime Agent 'my-first-agent' deployed successfully."
}
```
```

--------------------------------

### Get Started with Miniflare for Cloudflare Workers Testing

Source: https://developers.cloudflare.com/llms.txt

This guide provides instructions on getting started with Miniflare, a local simulator for Cloudflare Workers. It's essential for local development and testing of your Workers applications.

```plaintext
This section focuses on the initial steps for using Miniflare. Practical examples and setup instructions are available in the linked documentation.
```

--------------------------------

### WebAuthn API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for WebAuthn, covering getting started with the API and SDK.

```APIDOC
## WebAuthn API

### Description
This section provides API documentation for WebAuthn, including getting started with both the API and the SDK.

### Resources
- Getting started with the API: [/docs/guides/webauthn/api]
- Getting started with the SDK: [/docs/guides/webauthn/sdk]
```

--------------------------------

### Example Command Execution (Shell)

Source: https://modelcontextprotocol.io/quickstart/user

This example shows how to execute the filesystem server using Node.js's npx tool. The command includes flags for automatic confirmation and specifies the package to install and run, along with the directories it can access.

```bash
npx @modelcontextprotocol/server-filesystem -y /path/to/directory1 /path/to/username
```

--------------------------------

### Deploy Realtime Agent using CLI

Source: https://developers.cloudflare.com/llms.txt

This guide provides instructions on deploying your first Cloudflare Realtime Agent using the command-line interface (CLI). It outlines the necessary steps and commands to get started.

```bash
# Example CLI command to deploy a Realtime Agent
# Note: Actual command will vary based on the specific CLI tool and agent configuration.
# Refer to the official Cloudflare Realtime Agents documentation for exact commands.

# cloudflare-realtime agent deploy --name my-agent --config ./agent-config.yaml
```

--------------------------------

### Getting Started with REST API

Source: https://developers.cloudflare.com/llms.txt

Begin using the Cloudflare Workers AI REST API to deploy your first large language model (LLM) with step-by-step guidance.

```APIDOC
## Getting Started with REST API

### Description
This guide provides instructions on how to deploy a large language model (LLM) using the Cloudflare Workers AI REST API. It is designed for users new to the platform.

### Endpoint
[https://developers.cloudflare.com/workers-ai/get-started/rest-api/](https://developers.cloudflare.com/workers-ai/get-started/rest-api/)

### Usage
Follow the steps in the linked guide to set up and start using the Workers AI REST API.
```

--------------------------------

### Cloudflare Images - Overview

Source: https://developers.cloudflare.com/llms.txt

This section provides an overview of Cloudflare Images, its capabilities, and links to key resources such as demos, getting started guides, pricing, and the full API reference.

```APIDOC
## Cloudflare Images Overview

Cloudflare Images allows you to streamline your image infrastructure by efficiently storing, transforming, and delivering images using Cloudflare's global network.

### Key Resources:
- **Demos and Architectures:** [https://developers.cloudflare.com/images/demos/index.md](https://developers.cloudflare.com/images/demos/index.md)
- **Getting Started:** [https://developers.cloudflare.com/images/get-started/index.md](https://developers.cloudflare.com/images/get-started/index.md)
- **Images API Reference:** [https://developers.cloudflare.com/images/images-api/index.md](https://developers.cloudflare.com/images/images-api/index.md)
- **Pricing:** [https://developers.cloudflare.com/images/pricing/index.md](https://developers.cloudflare.com/images/pricing/index.md)
- **Examples:** [https://developers.cloudflare.com/images/examples/index.md](https://developers.cloudflare.com/images/examples/index.md)
```

--------------------------------

### JavaScript: Start and Handle Errors for Stateless HTTP Server

Source: https://github.com/modelcontextprotocol/typescript-sdk

This JavaScript code snippet demonstrates how to start a stateless HTTP server and handle potential errors during its setup or execution. It logs server status and exits with an error code if setup fails. This approach is suitable for simple API wrappers, RESTful scenarios, and horizontally scaled deployments.

```javascript
try {
  // ... server setup code ...
  console.log(`MCP Stateless Streamable HTTP Server listening on port ${PORT}`);
} catch (error) {
  console.error('Failed to set up the server:', error);
  process.exit(1);
}
process.exit(0);
```

--------------------------------

### Build Client

Source: https://modelcontextprotocol.io/quickstart/user

Get started building your own client that can integrate with all MCP servers.

```APIDOC
## Build Client

### Description
Get started building your own client that can integrate with all MCP servers.

### Method
GET

### Endpoint
/docs/develop/build-client

### Parameters
None

### Request Example
None

### Response
None
```

--------------------------------

### Example Prompt: Get HTML Content

Source: https://github.com/cloudflare/mcp-server-cloudflare/tree/main/apps/browser-rendering

This is an example prompt demonstrating how to request the HTML content of a specific URL using the available tools. It specifies the action and the target URL.

```text
Get the HTML content of https://example.com.
```

--------------------------------

### Build Server

Source: https://modelcontextprotocol.io/quickstart/user

Get started building your own server to use in Claude for Desktop and other clients.

```APIDOC
## Build Server

### Description
Get started building your own server to use in Claude for Desktop and other clients.

### Method
GET

### Endpoint
/docs/develop/build-server

### Parameters
None

### Request Example
None

### Response
None
```

--------------------------------

### Low-Level Server Setup with Request Handlers

Source: https://github.com/modelcontextprotocol/typescript-sdk

Illustrates setting up a low-level Server instance with custom request handlers for specific schemas using the @modelcontextprotocol/sdk. This includes defining handlers for listing and getting prompts, and connecting the server to a StdioServerTransport. The server is configured with prompt capabilities.

```javascript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
  ListPromptsRequestSchema,
  GetPromptRequestSchema
} from "@modelcontextprotocol/sdk/types.js";

const server = new Server(
  {
    name: "example-server",
    version: "1.0.0"
  },
  {
    capabilities: {
      prompts: {}
    }
  }
);

server.setRequestHandler(ListPromptsRequestSchema, async () => {
  return {
    prompts: [{
      name: "example-prompt",
      description: "An example prompt template",
      arguments: [{
        name: "arg1",
        description: "Example argument",
        required: true
      }]
    }]
  };
});

server.setRequestHandler(GetPromptRequestSchema, async (request) => {
  if (request.params.name !== "example-prompt") {
    throw new Error("Unknown prompt");
  }
  return {
    description: "Example prompt",
    messages: [{
      role: "user",
      content: {
        type: "text",
        text: "Example prompt text"
      }
    }]
  };
});

const transport = new StdioServerTransport();
await server.connect(transport);
```

--------------------------------

### Install GitHub MCP Server with Flexible Configuration

Source: https://docs.windsurf.com/windsurf/cascade/mcp

This configuration allows users to install the GitHub MCP server with any valid configuration, as long as the server ID matches the plugin store entry. This provides flexibility in setup while maintaining a defined server identity.

```json
{
  "command": "docker",
  "args": [
    "run",
    "-i",
    "--rm",
    "-p",
    "3000:3000",
    "--add-host=host.docker.internal:host-gateway",
    "ghcr.io/cloudflare/cloudflared:latest",
    "--proxy-dns",
    "--proxy-dns-upstream",
    "8.8.8.8:53",
    "--proxy-dns-upstream",
    "1.1.1.1:53",
    "--url",
    "http://localhost:3000",
    "tunnel",
    "--token",
    "$TUNNEL_TOKEN"
  ]
}
```

--------------------------------

### Deploy Example MCP Server to Cloudflare

Source: https://developers.cloudflare.com/agents/guides/remote-mcp-server/

This snippet utilizes a 'Deploy to Workers' button to facilitate the deployment of an example MCP server to a Cloudflare account. It assumes the user has a Cloudflare account and provides a direct link for easy setup. The deployment configures a new git repository for automatic deployments.

```HTML
<a href="https://deploy.workers.cloudflare.com/?url=https://github.com/cloudflare/ai/tree/main/demos/remote-mcp-authless">
  <img src="https://deploy.workers.cloudflare.com/button" alt="Deploy to Workers">
</a>
```

--------------------------------

### Install and Run Cloudflare Agents LLMs Locally

Source: https://github.com/cloudflare/ai/tree/main/demos/remote-mcp-server

This snippet provides the necessary shell commands to clone the Cloudflare AI repository, install its dependencies using pnpm, and start the local development server. It assumes a Unix-like environment and the presence of git and pnpm. The output is a running local server accessible at http://localhost:8787/.

```shell
# clone the repository
git clone https://github.com/cloudflare/ai.git
# Or if using ssh:
# git clone git@github.com:cloudflare/ai.git

# install dependencies
cd ai
# Note: using pnpm instead of just "npm"
pnpm install

# run locally
npx nx dev remote-mcp-server
```

--------------------------------

### Flexible LLM Server Installation using Environment Variables

Source: https://docs.windsurf.com/windsurf/cascade/mcp

This code snippet demonstrates how to configure environment variables for installing the GitHub MCP server with a flexible configuration. It allows for any valid server configuration provided the server ID matches the plugin store entry. This is useful for dynamic setups where specific token values might change.

```json
{
  "rm": ",",
  "-e": ","
},
{
  "GITHUB_PERSONAL_ACCESS_TOKEN": ","
},
{
  "ghcr.io/github/github-mcp-server": ","
},
{
  "env": {
    "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
  }
}
```

--------------------------------

### Durable Objects Examples

Source: https://developers.cloudflare.com/durable-objects/what-are-durable-objects/

Practical examples demonstrating how to implement various features with Durable Objects.

```APIDOC
## Durable Objects Examples

### Build a Rate Limiter
Example code for creating a rate limiter using Durable Objects.

### Build a Counter
Demonstration of how to build a distributed counter with Durable Objects.

### Build a WebSocket Server
Example of implementing a WebSocket server using Durable Objects.

### Build a WebSocket Server with WebSocket Hibernation
Advanced example for WebSocket servers with hibernation support.

### Durable Object In-memory State
Example showcasing the use of in-memory state within Durable Objects.

### Testing with Durable Objects
Code examples and guidance for testing applications that utilize Durable Objects.
```

--------------------------------

### Setup Pipeline

Source: https://developers.cloudflare.com/workers/wrangler/commands/

Initiates an interactive setup process for creating a complete pipeline.

```APIDOC
## POST /pipelines/setup

### Description
Interactive setup for a complete pipeline.

### Method
POST

### Endpoint
/pipelines/setup

### Parameters
#### Query Parameters
- **--name** (string) - Optional - Pipeline name.

### Request Example
```json
{
  "--name": "interactive-pipeline"
}
```

### Response
#### Success Response (201)
- **message** (string) - Confirmation message for the setup process.

#### Response Example
```json
{
  "message": "Pipeline setup initiated successfully."
}
```
```

--------------------------------

### Example Container Styling

Source: https://developers.cloudflare.com/agents/api-reference/rag/

Provides specific styling for elements intended to display examples. It ensures these containers have a distinct background, border, and are displayed as blocks, making example code or content visually separate from the main page.

```css
.example-container {
  display: block !important;
  background-color: var(--sl-color-bg) !important;
  border-color: var(--sl-color-hairline) !important;
}
```

--------------------------------

### Recipes and Examples for Vitest Workers Integration

Source: https://developers.cloudflare.com/llms.txt

Explore various recipes and examples demonstrating how to write unit and integration tests for Cloudflare Workers using the Vitest integration. These examples cover common use cases and patterns.

```plaintext
This section provides practical examples for testing Workers with Vitest. Code snippets and usage scenarios are available in the linked documentation.
```

--------------------------------

### JavaScript Example

Source: https://developers.cloudflare.com/agents/api-reference/http-sse/

Example of implementing the `onRequest` method in JavaScript.

```APIDOC
## JavaScript Agent Example

### Description
This example demonstrates how to create an Agent class in JavaScript and implement the `onRequest` method to handle HTTP requests.

### Method
POST

### Endpoint
/

### Request Body
- **request** (Request) - Required - The incoming HTTP request object.

### Code
```javascript
class MyAgent extends Agent {
  // Handle HTTP requests coming to this Agent instance
  // Returns a Response object
  async onRequest(request) {
    return new Response("Hello from Agent!");
  }

  async callAIModel(prompt) {
    // Implement AI model call here
  }
}
```
```

--------------------------------

### Install NPM Globally

Source: https://modelcontextprotocol.io/quickstart/user

This command installs Node Package Manager (NPM) globally on your system. Global installation is often a prerequisite for using commands like `npx` successfully, especially when troubleshooting server startup issues.

```shell
npm install -g npm
```

--------------------------------

### Rust - Basic 'Hello World' Program

Source: https://modelcontextprotocol.io/docs/concepts/resources

This snippet demonstrates a simple 'Hello, world!' program in Rust. It includes the standard main function and the println! macro for output. This is a fundamental example for getting started with Rust programming.

```rust
fn main() {
 println!("Hello world!");
}
```

--------------------------------

### Create Cloudflare Agents Starter Project

Source: https://github.com/cloudflare/agents-starter

Use npx to create a new Cloudflare project with the agents-starter template. This command initializes a new project directory with the necessary files and configurations for a Cloudflare Agent application.

```shell
npx create-cloudflare@latest --template cloudflare/agents-starter
```

--------------------------------

### Example User Configuration (JSON) - Basic

Source: https://docs.windsurf.com/windsurf/cascade/mcp

This JSON snippet demonstrates a basic user configuration for MCP, likely intended to match a specific server. It includes settings for the server ID, command, and arguments, illustrating how users can define their own server configurations.

```json
{
  "server_id": "github-mcp-server",
  "command": "mcp:command",
  "args": [
    "arg1",
    "arg2"
  ]
}
```

--------------------------------

### Install Agents Package in Existing Project

Source: https://developers.cloudflare.com/agents

Command to install the 'agents' npm package into an existing Cloudflare Workers project. This allows you to integrate Agent functionality into your current setup.

```shell
npm i agents
```

--------------------------------

### Configure Filesystem Server for Claude Desktop (JSON)

Source: https://modelcontextprotocol.io/quickstart/user

This JSON configuration tells Claude Desktop to start the Filesystem Server using npx. It specifies the server package and the directories the server will have access to. Ensure you replace 'username' with your actual username and adjust directory paths as needed.

```json
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/username/Desktop",
        "/Users/username/Downloads"
      ]
    }
  }
}
```

--------------------------------

### Initialize and Deploy Agent Starter Template

Source: https://developers.cloudflare.com/agents

Commands to install the Agent starter template and deploy it using Wrangler. This is the initial step to create a new Agent project.

```shell
# install it
npm create cloudflare@latest agents-starter -- --template=cloudflare/agents-starter
# and deploy it
npx wrangler@latest deploy
```

--------------------------------

### JavaScript Server Setup and Prompt Handling with Cloudflare Agents LLM SDK

Source: https://github.com/modelcontextprotocol/typescript-sdk

This snippet shows how to set up a server using the Cloudflare Agents LLM SDK in JavaScript. It includes importing necessary modules, initializing the server with a name, version, and prompt capabilities, and defining handlers for 'ListPrompts' and 'GetPrompt' requests. The handlers return predefined prompt data and handle unknown prompts with an error. Finally, it connects the server to the StdioServerTransport.

```javascript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
 ListPromptsRequestSchema,
 GetPromptRequestSchema
} from "@modelcontextprotocol/sdk/types.js";

const server = new Server(
 {
 name: "example-server",
 version: "1.0.0"
 },
 {
 capabilities: {
 prompts: {}
 }
}
);

server.setRequestHandler(ListPromptsRequestSchema, async () => {
 return {
 prompts: [{
 name: "example-prompt",
 description: "An example prompt template",
 arguments: [{
 name: "arg1",
 description: "Example argument",
 required: true
 }]
 }]
 };
});

server.setRequestHandler(GetPromptRequestSchema, async (request) => {
 if (request.params.name !== "example-prompt") {
 throw new Error("Unknown prompt");
 }
 return {
 description: "Example prompt",
 messages: [{
 role: "user",
 content: {
 type: "text",
 text: "Example prompt text"
 }
 }]
 };
});

const transport = new StdioServerTransport();
await server.connect(transport);
```

--------------------------------

### README - Project Overview

Source: https://github.com/cloudflare/mcp-server-cloudflare/tree/main/apps/browser-rendering

This README file provides an overview of the Cloudflare Browser Rendering MCP Server. It includes a title and a brief description of the project's purpose.

```markdown
# Cloudflare Browser Rendering MCP Server 📡

This project provides a server for rendering web pages using Cloudflare Workers.
```

--------------------------------

### Passwords API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for Passwords, including getting started with the API and SDK, and password strength policy.

```APIDOC
## Passwords API

### Description
This section provides API documentation for Passwords, covering getting started with the API and SDK, and information on password strength policies.

### Resources
- Getting started with the API: [/docs/guides/passwords/api]
- Getting started with the SDK: [/docs/guides/passwords/sdk]
- Password strength policy: [/docs/guides/passwords/strength-policy]
- Email verification before password creation: [/docs/guides/passwords/email-verification/before-password-creation]
- Email verification after password creation: [/docs/guides/passwords/email-verification/after-password-creation]
```

--------------------------------

### Embeddable Magic Links API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for Embeddable Magic Links, focusing on how to get started with the API.

```APIDOC
## Embeddable Magic Links API

### Description
This section provides API documentation for Embeddable Magic Links.

### Resources
- Getting started with the API: [/docs/guides/magic-links/embeddable-magic-links/api]
```

--------------------------------

### MCP Server Configuration Example (JSON)

Source: https://docs.windsurf.com/windsurf/cascade/mcp

An example of the mcp_config.json file, demonstrating how to configure an MCP server connection for GitHub. This JSON file specifies the command and arguments to run for the MCP server.

```json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",

```

--------------------------------

### Passkeys API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for Passkeys, including overview and setup with the frontend SDK.

```APIDOC
## Passkeys API

### Description
This section details the API for Passkeys, including an overview and instructions for setting up Passkeys with the frontend SDK.

### Resources
- Passkeys overview: [/docs/guides/passkeys/overview]
- Set up Passkeys with the frontend SDK: [/docs/guides/passkeys/login-sdk]
```

--------------------------------

### Resource Annotations Example

Source: https://modelcontextprotocol.io/docs/concepts/resources

Example JSON structure demonstrating resource annotations for audience, priority, and lastModified. These annotations provide hints to clients on how to use or display resources.

```json
{
  "uri": "file:///project/README.md",
  "name": "README.md",
  "title": "Project Documentation",
  "mimeType": "text/markdown",
  "annotations": {
    "audience": ["user"],
    "priority": 0.8,
    "lastModified": "2025-01-12T15:00:58Z"
  }
}
```

--------------------------------

### Passcodes API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for Passcodes, including getting started with the API and SDK, and information on SMS toll fraud prevention.

```APIDOC
## Passcodes API

### Description
This section provides API documentation for Passcodes, covering getting started with the API and SDK, and resources related to SMS toll fraud prevention.

### Resources
- Getting started with the API: [/docs/guides/passcodes/api]
- Getting started with the SDK: [/docs/guides/passcodes/sdk]
- What is SMS toll fraud?: [/docs/guides/passcodes/toll-fraud/overview]
- How you can prevent toll fraud: [/docs/guides/passcodes/toll-fraud/guide]
- Unsupported countries: [/docs/guides/passcodes/unsupported-countries]
```

--------------------------------

### Hono Application Deployment on Cloudflare Workers

Source: https://developers.cloudflare.com/llms.txt

This guide explains how to create and deploy a Hono application to Cloudflare Workers with Workers Assets. It includes setup and publishing instructions.

```javascript
import { Hono } from 'hono'

const app = new Hono()

app.get('/', (c) => {
  return c.text('Hello Hono!')
})

export default {
  async fetch(request, env) {
    return app.fetch(request)
  }
}
```

--------------------------------

### Manually Run Filesystem Server (Windows)

Source: https://modelcontextprotocol.io/quickstart/user

This command manually initiates the Filesystem Server from the command line on Windows. It requires specifying the absolute paths for the directories the server should access. Ensure Node Package Manager (NPM) is installed.

```shell
npx -y @modelcontextprotocol/server-filesystem C:\Users\username\Desktop C:\Users\username\Downloads
```

--------------------------------

### Example Package JSON (JSON)

Source: https://github.com/cloudflare/mcp-server-cloudflare/tree/main/apps/autorag

This is a package.json file, which manages project dependencies and scripts for a Node.js project. It lists development dependencies like TypeScript, ESLint, and Vitest, along with build and test scripts.

```json
{
  "name": "autorag",
  "version": "0.1.0",
  "private": true,
  "scripts": {
    "dev": "wrangler dev",
    "start": "wrangler dev",
    "build": "tsc",
    "test": "vitest"
  },
  "dependencies": {
    "@cloudflare/workers-types": "^4.0.0",
    "wrangler": "^3.0.0"
  },
  "devDependencies": {
    "@types/node": "^18.0.0",
    "@typescript-eslint/eslint-plugin": "^5.0.0",
    "@typescript-eslint/parser": "^5.0.0",
    "eslint": "^8.0.0",
    "eslint-config-prettier": "^8.0.0",
    "prettier": "^2.0.0",
    "typescript": "^5.0.0",
    "vitest": "^1.0.0"
  }
}
```

--------------------------------

### Connect to PostgreSQL Database with Cloudflare Workers

Source: https://developers.cloudflare.com/llms.txt

This guide explains how to establish a connection to a PostgreSQL database from Cloudflare Workers. It outlines the necessary setup and code to perform database operations.

```javascript
import postgres from 'postgres'

const sql = postgres({
  host: env.PGHOST,
  port: env.PGPORT,
  database: env.PGDATABASE,
  username: env.PGUSER,
  password: env.PGPASSWORD
})

export default {
  async fetch(request) {
    try {
      const users = await sql`SELECT * FROM users`
      return new Response(JSON.stringify(users))
    } catch (error) {
      return new Response(JSON.stringify({ error: error.message }), {
        status: 500
      })
    }
  }
}
```

--------------------------------

### Filesystem Server Configuration (JSON)

Source: https://modelcontextprotocol.io/quickstart/user

This JSON snippet demonstrates the configuration for a filesystem server, including its friendly name, the command to run it, and the package name. It also specifies the directories the server is allowed to access.

```json
{
  "filesystem": "friendly_server_name",
  "command": "npx",
  "-y": "",
  "@modelcontextprotocol/server-filesystem": "",
  "args": [
    "/path/to/directory1",
    "/path/to/username"
  ]
}
```

--------------------------------

### Worker-to-Worker Communication via RPC Bindings

Source: https://developers.cloudflare.com/llms.txt

This guide details how to enable Worker-to-Worker communication using RPC (Remote Procedure Call) Bindings. It outlines the setup for invoking functions in one Worker from another.

```javascript
// In Worker A
export default {
  async fetch(request, env) {
    const result = await env.RPC_WORKER.increment(1)
    return new Response(String(result))
  }
}

// In Worker B (RPC_WORKER)
import { exportrpc } from '@cloudflare/workers-types'

let count = 0

export default {
  async fetch(request) {
    return exportrpc('increment', async (value) => {
      count += value
      return count
    })
  }
}
```

--------------------------------

### MCP Configuration JSON Example

Source: https://docs.windsurf.com/windsurf/cascade/mcp

This JSON snippet demonstrates the structure of `mcp_config.json`, used to define servers that Cascade can connect to. It includes server details like commands and arguments, following a schema compatible with Claude Desktop configurations. This example specifically configures a server for GitHub.

```json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        
      ]
    }
  }
}
```

--------------------------------

### Get Traffic Anomalies List

Source: https://github.com/cloudflare/mcp-server-cloudflare/tree/main/apps/radar

Lists traffic anomalies and outages, with filtering capabilities by AS, location, start date, and end date. This function helps identify unusual network traffic patterns.

```python
get_traffic_anomalies()
```

--------------------------------

### Manually Run Filesystem Server (macOS/Linux)

Source: https://modelcontextprotocol.io/quickstart/user

This command manually initiates the Filesystem Server from the command line on macOS or Linux. It requires specifying the absolute paths for the directories the server should access. Ensure Node Package Manager (NPM) is installed.

```shell
npx -y @modelcontextprotocol/server-filesystem /Users/username/Desktop /Users/username/Downloads
```

--------------------------------

### Run Cloudflare Inspector with Docker

Source: https://github.com/modelcontextprotocol/inspector

This command starts the Cloudflare inspector within a Docker container. It allows for isolated execution of the inspector tool. Ensure Docker is installed and running on your system.

```shell
docker run -p 6274:6274 @modelcontextprotocol/inspector
```

--------------------------------

### Range Query with Strings for Prefix Filtering

Source: https://developers.cloudflare.com/vectorize/reference/metadata-filtering/

This example illustrates how range queries can be used for prefix searching on string metadata. By setting '$gte' to 'net' and '$lt' to 'neu', it effectively filters for string values that start with 'net'.

```json
{
  "someKey": { "$gte": "net", "$lt": "neu" }
}
```

--------------------------------

### HTML Structure for MCP Client Demo

Source: https://github.com/cloudflare/ai/tree/main/demos/mcp-client

This is the main HTML file (`index.html`) for the MCP Client demo. It sets up the basic structure of the web page, including meta tags, a title, and links to the application's styles and scripts. It serves as the entry point for the user interface of the AI agent.

```html
<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <link rel="icon" type="image/svg+xml" href="/ai.svg" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>MCP Client</title>
    <script type="module" crossorigin src="/assets/index-3b3f962e.js"></script>
    <link rel="stylesheet" crossorigin href="/assets/index-032d7278.css">
  </head>
  <body>
    <div id="root"></div>
    
  </body>
</html>

```

--------------------------------

### Email Magic Links API

Source: https://stytch.com/docs/guides/connected-apps/mcp-servers

API documentation for Email Magic Links, covering getting started with the API, SDK, replacing password reset flows, building invite user flows, adding magic links to existing auth flows, PKCE, and redirect routing.

```APIDOC
## Email Magic Links API

### Description
This section details the API for Email Magic Links, including setup, integration with existing flows, and advanced configurations.

### Resources
- Getting started with the API: [/docs/guides/magic-links/email-magic-links/api]
- Getting started with the SDK: [/docs/guides/magic-links/email-magic-links/sdk]
- Replacing your password reset flow: [/docs/guides/magic-links/email-magic-links/replace-password-reset]
- Building an invite user flow: [/docs/guides/magic-links/email-magic-links/invite-user]
- Add magic links to an existing auth flow: [/docs/guides/magic-links/email-magic-links/existing-auth]
- Adding PKCE to a Magic Link flow: [/docs/guides/magic-links/email-magic-links/adding-pkce]
- Magic Link redirect routing: [/docs/guides/magic-links/email-magic-links/redirect-routing]
```

--------------------------------

### Fetch data from an Agent using agentFetch (JavaScript)

Source: https://developers.cloudflare.com/agents/api-reference/agents-api/

Provides an example of using the agentFetch function in JavaScript to make a GET request to a 'task-manager' Agent instance named 'user-123-tasks'. It includes error handling for the HTTP request and parsing the JSON response.

```javascript
import { agentFetch } from "agents/client";

// Function to get data from an Agent
async function fetchAgentData() {
  try {
    const response = await agentFetch(
      {
        agent: "task-manager",
        name: "user-123-tasks",
      },
      {
        method: "GET",
        headers: {
          Authorization: `Bearer ${userToken}`,
        },
      }
    );

    if (!response.ok) {
      throw new Error(`Error: ${response.status}`);
    }

    const data = await response.json();
    return data;
  } catch (error) {
    console.error("Failed to fetch from agent:", error);
  }
}
```

--------------------------------

### Example User Configuration (mcp_config.json)

Source: https://docs.windsurf.com/windsurf/cascade/mcp

This JSON file demonstrates a user-specific configuration that should match the defined server whitelist patterns, allowing the agent to connect and operate correctly.

```json
{
  "command": "python3",
  "args": [
    "mcp-server.py",
    "--port",
    "8000"
  ]
}
```

--------------------------------

### Cloudflare Hyperdrive: Connect to PostgreSQL (TypeScript)

Source: https://developers.cloudflare.com/workers/get-started/prompting/

This example shows how to connect to and query a PostgreSQL database using Cloudflare Hyperdrive with the Postgres.js library. It includes the necessary environment variable setup for Hyperdrive and demonstrates executing a simple query.

```typescript
// Postgres.js 3.4.5 or later is recommended
import postgres from "postgres";

export interface Env {
  // If you set another name in the Wrangler config file as the value for 'binding',
  // replace "HYPERDRIVE" with the variable name you defined.
  HYPERDRIVE: Hyperdrive;
}

export default {
  async fetch(request, env, ctx): Promise<Response> {
    console.log(JSON.stringify(env));
    // Create a database client that connects to your database via Hyperdrive.
    // Hyperdrive generates a unique connection string you can pass to
    // supported drivers, including node-postgres, Postgres.js, and the many
    // ORMs and query builders that use these drivers.
    const sql = postgres(env.HYPERDRIVE.connectionString)

    try {
      // Test query
      const results = await sql`SELECT * FROM pg_tables`;
      // Return result rows as JSON
      return Response.json(results);
    } catch (e) {
      console.error(e);
      return Response.json(
        { error: e instanceof Error ? e.message : e },
        { status: 500 },
      );
    }
  }

} satisfies ExportedHandler<Env>;

```

--------------------------------

### Get User Profile and Token from Identity Provider (Ruby)

Source: https://workos.com/

This Ruby snippet shows how to use the WorkOS gem to retrieve a user's access token and profile information from an Identity Provider. Ensure the WorkOS gem is installed and configured with your API key.

```ruby
require 'workos'

WorkOS.key = 'sk_example_123456789'

WorkOS::SSO.profile_and_token(
  code: '01E2RJ4C05B52KKZ8FSRDAP23J',
  client_id: 'client_123456789',
)
```