Goldilocks
Verified IntegrationClient Configuration
— Connect Goldilocks to Claude Desktop or Cursor in seconds{
"mcpServers": {
"goldilocks": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-goldilocks"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Predicts optimal k-point distances and grids for SCF DFT calculations using machine learning models trained on Quantum ESPRESSO data.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Goldilocks
Goldilocks allows users to specify confidence levels for its predictions. The models are trained to provide estimates at 0.85, 0.9, and 0.95 confidence levels for both k-point distance estimation and grid generation.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.