I built CloudHike: a backend your AI coding agent can set up over MCP

说明与用途

开发者可以使用 CloudHike 和 MCP 快速部署完整后端，消除手动设置数据库、存储和身份验证的步骤。

问题

AI coding agents can write full-stack code but struggle with backend provisioning—creating databases, storage, auth, email, and managing secrets—leading to lost momentum and multiple dashboards.

结果

Developers can now set up complete backends in a single prompt, reducing manual configuration to a few clicks and keeping secrets out of source control.

工作流

• Configure MCP server URL and API key in the editor
• Agent analyzes app code to determine required services
• Agent calls list_projects or create_project to obtain a project
• Agent calls deploy_services for needed services and waits until ready
• Agent calls get_environment to retrieve .env variables and writes them to .env.local
• Agent calls get_docs to fetch relevant documentation and generates connection code

证据

My AI agent can write a whole Next.js app in an afternoon. Then it stops and hands the hard part back to me: make a Postgres database, set up a storage bucket, find a Redis instance, add auth, pick an email provider, and copy a dozen connection strings into .env.local without committing any of them.

来源

CloudHike is a backend-as-a-service built for people who code with AI agents. Each project can have: Postgres, S3-compatible storage, Redis, Auth, Transactional email, Background jobs.

来源

The part I care about most is the remote MCP server. Once you add it to your editor, your agent can do the backend setup itself.

来源

With the server connected, open your app's folder and paste this prompt (it's from the docs): Use the cloudhike MCP tools to set up CloudHike.dev as the backend for this app.

来源