Heim MCP
A MCP server do create and deploy backend applications using https://heim.dev
README
Heim MCP
Model Context Protocol server for Heim application deployment and management.
Overview
This MCP server allows AI agents like Claude Desktop, Cursor, Windsurf, and others to create, deploy, and manage Heim applications directly through natural language commands.
Purpose You can directly ask the AI to create new Heim applications from OpenAPI specifications, deploy them locally or to the cloud, and manage the Heim runtime.
What is Heim? Heim is a platform for creating and deploying backend applications.
Available Tools
| Tool | Description |
|---|---|
new_heim_application |
Creates a new Heim application from an OpenAPI 3.0.1 specification |
deploy_heim_application |
Deploys an application to the local Heim runtime (available at http://127.0.0.1:3000) |
deploy_heim_application_to_cloud |
Deploys an application to Heim cloud |
start_heim |
Starts the Heim runtime to handle deployment requests |
clear_heim |
Clears the local cache and stops the Heim runtime |
update_heim |
Updates Heim to the latest version |
Using with Cursor
Installation - Globally
Run the MCP server using npx:
npx -y @nor2/heim-mcp@latest
In your Cursor IDE
- Go to
Cursor Settings>MCP - Click
+ Add New MCP Server - Fill in the form:
- Name:
Heim(or any name you prefer) - Type:
command - Command:
npx -y @nor2/heim-mcp@latest
- Name:
Installation - Project-specific
Add an .cursor/mcp.json file to your project:
{
"mcpServers": {
"heim": {
"command": "npx",
"args": [
"-y",
"@nor2/heim-mcp@latest"
]
}
}
}
Usage
Once configured, the Heim tools will be automatically available to the Cursor AI Agent. You can:
- Ask the AI to create new applications from OpenAPI specs
- Deploy applications locally or to the cloud
- Manage the Heim runtime
- The tools will be listed under
Available Toolsin MCP settings
Using with Roo Code
Access the MCP settings by clicking "Edit MCP Settings" in Roo Code settings or using the "Roo Code: Open MCP Config" command in VS Code's command palette.
{
"mcpServers": {
"heim": {
"command": "npx",
"args": [
"-y",
"@nor2/heim-mcp@latest"
]
}
}
}
Prerequisites
Before using this MCP server, you need to have Heim installed on your system. You can install it by following the instructions at https://heim.dev/releases/.
Development
# Install dependencies
pnpm install
# Build
pnpm build
Debugging the Server
To debug your server, you can use the MCP Inspector.
First build the server:
pnpm build
Run the following command in your terminal:
# Start MCP Inspector and server with all tools
npx @modelcontextprotocol/inspector node dist/index.js
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。