R

Remote MCP Server On Cloudflare Wt0

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement the OAuth login function. It supports local development and debugging, allows connection to the service through the MCP Inspector or Claude Desktop application, and is finally deployed to Cloudflare for remote client invocation.
2 points
13

What is the Remote MCP Server?

The Remote MCP Server is a remote service based on the Model Context Protocol (MCP), deployed on Cloudflare Workers. It allows developers to interact with AI models through the SSE (Server-Sent Events) protocol and provides an OAuth login authentication mechanism.

How to use the Remote MCP Server?

You can connect to the MCP server through the MCP Inspector tool or the Claude Desktop client to invoke predefined tool functions. It supports both local development and cloud deployment modes.

Applicable scenarios

Suitable for scenarios where the capabilities of AI tools need to be integrated into applications, especially AI services that require remote access and OAuth authentication.

Main features

Remote SSE connectionSupports remote connection to the MCP server through the Server-Sent Events protocol
OAuth authenticationProvides a user login authentication mechanism based on OAuth
Tool invocationSupports defining and invoking various AI tools (such as math calculation tools)
Multi-client supportCompatible with multiple clients such as MCP Inspector and Claude Desktop

Advantages and limitations

Advantages
Based on Cloudflare Workers, with global distributed deployment
Supports both local development and cloud deployment modes
Provides an OAuth authentication mechanism, with high security
Compatible with multiple MCP client tools
Limitations
Requires KV storage configuration for OAuth
Requires certain technical configuration for initial use
Depends on the Cloudflare platform

How to use

Set up the local development environment
Clone the repository and install dependencies
Start the local server
Run the local development server
Connect using the MCP Inspector
Start the MCP Inspector and connect to the local server
Deploy to Cloudflare
Create a KV namespace and deploy to Cloudflare Workers
Configure Claude Desktop
Modify the Claude configuration to connect to the remote MCP server

Usage examples

Invocation of the math calculation toolInvoke the math calculation tool through the Claude client for addition operations
Invocation of remote toolsConnect to the MCP server deployed on Cloudflare from a remote client

Frequently Asked Questions

What should I do if the connection fails?
How can I view the available tools?
What should I do if the KV configuration fails during deployment?

Related resources

MCP official documentation
Official documentation for the Model Context Protocol
Cloudflare Workers documentation
Development documentation for Cloudflare Workers
GitHub repository
Project source code
Anthropic quick start
Configuration guide for Claude Desktop
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"
      ]
    }
  }
}

{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://worker-name.account-name.workers.dev/sse"
      ]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
100
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
153
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
840
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
575
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
761
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase