EdgeOne Pages MCP
About
An MCP server implementation using EdgeOne Pages Functions for intelligent chat applications.
Details
- Author
- xpecia1
- Categories
- Developer Tools, Infrastructure, Cloud Service
Jump to
Setup
Install EdgeOne Pages MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/xpecia1/mcp-on-edge
Follow the installation instructions in the repository README, then restart your MCP client.
An MCP server implementation using EdgeOne Pages Functions for intelligent chat applications.
EdgeOne Pages: MCP Client and Server Implementation with Functions
This project showcases an intelligent chat application built with EdgeOne Pages Functions technology. It interacts with backend functions through a web interface, implementing a complete Model Context Protocol (MCP) workflow.
The system architecture consists of the following core components:
- MCP Streamable HTTP Server (functions/mcp-server/index.ts)
- MCP Client (functions/mcp-client/index.ts)
- Backend API (functions/v1/chat/completions/index.ts) as the MCP HOST, responsible for coordinating the entire MCP workflow
Through this architecture, users can access powerful MCP tool capabilities in the browser, enabling intelligent interactions such as "generating online webpages with a single prompt."
- Interactive Chat Interface:Modern, responsive web interface built with Next.js and React
- High-Performance Edge Functions:Critical business logic deployed on highly scalable EdgeOne Pages Functions
- Complete MCP Implementation:Model Context Protocol implementation based on the latest specifications, providing powerful context management and request routing capabilities
- OpenAI Format Compatible:Backend API fully supports OpenAI-formatted request and response handling
Configure remote MCP services in applications that supportStreamable HTTP MCP Server.
{ "mcpServers": { "edgeone-pages-mcp-server": { "url": "https://mcp-on-edge.edgeone.site/mcp-server" } } }
First, install dependencies and start the development server:
# Install dependencies npm install # Or use other package managers # yarn install / pnpm install / bun install # Start development server npm run dev # Or use other package managers # yarn dev / pnpm dev / bun dev
Configure environment variables: Copy the.env.examplefile and rename it to.env, then fill in your AI service interface configuration information.
After starting, visithttp://localhost:3000in your browser to view the application.
- Frontend Interface:app/page.tsxcontains the main page logic and UI components
- Backend Functions: All edge functions are in thefunctionsdirectory
- Chat API:functions/v1/chat/completions
- MCP Server:functions/mcp-server
- MCP Client:functions/mcp-client
- Next.js Documentation- Next.js framework features and API
- EdgeOne Pages Functions Documentation- Detailed explanation of EdgeOne serverless functions
- Model Context Protocol (MCP)- Implemented based on the 2025-03-26 version of Streamable HTTP transport
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
An example of a remote MCP server deployed on Cloudflare Workers without authentication.
A remote MCP server without authentication, designed for easy deployment on Cloudflare Workers.
An example of a remote MCP server without authentication, deployable on Cloudflare Workers or runnable locally.
A remote MCP server without authentication, deployable on Cloudflare Workers or locally with npm.
A remote MCP server deployable on Cloudflare Workers that does not require authentication.
A template for deploying a remote MCP server on Cloudflare Workers without authentication.
An example of deploying a customizable, remote MCP server on Cloudflare Workers without authentication.
An example MCP server deployed on Cloudflare Workers without authentication.
A remote MCP server example deployable on Cloudflare Workers, featuring customizable tools and no authentication.
An MCP server and client implementation for EdgeOne Pages Functions, supporting OpenAI-formatted requests.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
