Cursor MCP for Catapulta CLI
A Model Context Protocol (MCP) implementation for Catapulta CLI, enabling AI-powered interactions with deployment and management tools.
Catapulta MCP is a server implementation that bridges the gap between AI models and the Catapulta CLI, allowing for intelligent automation of deployment tasks and other operations. It provides a standardized way for AI models to interact with Catapulta’s functionality through a secure and controlled interface.
## Clone the repository
git clone https://github.com/catapulta-sh/catapulta-mcp.git
cd catapulta-mcp
## Install dependencies
npm install
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
// Create an MCP server
const server = new McpServer({
name: "catapulta-cli-server",
version: "0.1.0",
});
// Start the server with StdIO transport
const transport = new StdioServerTransport();
server.connect(transport).catch((error) => {
console.error("[MCP Error]", error);
process.exit(1);
});
// Example of generating a deployment command
const command = await server.tool("generate_deploy_command", {
script_path: "path/to/script",
network: "matic",
sponsor: true,
gas_hawk: true,
});
The following networks are supported for deployments:
The implementation includes several security measures:
## Build the project
npm run build
## Run tests
npm test
Paste this on the mcp.json
{
"mcpServers": {
"Catapulta-client": {
"command": "npx",
"args": ["-y", "@catapulta/mcp-server@latest"],
"env": {}
}
}
}
Paste this on the settings.json
{
"mcp": {
"servers": {
"Catapulta-client": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@catapulta/mcp-server@latest"]
}
}
}
}