
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 Tools
in 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.