article

README

Render MCP Server

Deploy to Render.com directly through AI assistants.

This MCP (Model Context Protocol) server allows AI assistants like Claude to interact with the Render API, enabling deployment and management of services on Render.com.

Features

List all services in your Render account
Get details of a specific service
Deploy services
Create new services
Delete services
Get deployment history
Manage environment variables
Manage custom domains

Installation

npm install -g @niyogi/render-mcp

Configuration

Get your Render API key from Render Dashboard
Configure the MCP server with your key:

node bin/render-mcp.js configure --api-key=YOUR_API_KEY

Alternatively, you can run node bin/render-mcp.js configure without the --api-key flag to be prompted for your API key.

Usage

Starting the Server

node bin/render-mcp.js start

Checking Configuration

node bin/render-mcp.js config

Running Diagnostics

node bin/render-mcp.js doctor

Note: If you've installed the package globally, you can also use the shorter commands:

render-mcp start
render-mcp config
render-mcp doctor

Using with Different AI Assistants

Using with Cline

Add the following to your Cline MCP settings file:

{
  "mcpServers": {
    "render": {
      "command": "node",
      "args": ["/path/to/render-mcp/bin/render-mcp.js", "start"],
      "env": {
        "RENDER_API_KEY": "your-render-api-key"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Restart Cline for the changes to take effect

You can now interact with Render through Claude:

Claude, please deploy my web service to Render

Using with Windsurf/Cursor

Install the render-mcp package:
```
npm install -g @niyogi/render-mcp
```

Configure your API key:

node bin/render-mcp.js configure --api-key=YOUR_API_KEY

Start the MCP server in a separate terminal:
```
node bin/render-mcp.js start
```
In Windsurf/Cursor settings, add the Render MCP server:
- Server Name: render
- Server Type: stdio
- Command: node
- Arguments: ["/path/to/render-mcp/bin/render-mcp.js", "start"]
You can now use the Render commands in your AI assistant

Using with Claude API Integrations

For custom applications using Claude's API directly:

Ensure the render-mcp server is running:
```
node bin/render-mcp.js start
```

In your application, when sending messages to Claude via the API, include the MCP server connections in your request:

{
  "mcpConnections": [
    {
      "name": "render",
      "transport": {
        "type": "stdio",
        "command": "node",
        "args": ["/path/to/render-mcp/bin/render-mcp.js", "start"]
      }
    }
  ]
}

Claude will now be able to interact with your Render MCP server

Example Prompts

Here are some example prompts you can use with Claude once the MCP server is connected:

"List all my services on Render"
"Deploy my web service with ID srv-123456"
"Create a new static site on Render from my GitHub repo"
"Show me the deployment history for my service"
"Add an environment variable to my service"
"Add a custom domain to my service"

Development

Building from Source

git clone https://github.com/niyogi/render-mcp.git
cd render-mcp
npm install
npm run build

Running Tests

npm test

License

MIT

Render微云平台