Mandoline
Verified IntegrationClient Configuration
— Connect Mandoline to Claude Desktop or Cursor in seconds{
"mcpServers": {
"mandoline": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mandoline"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Empowers large language models and AI assistants to conduct self-evaluations, critique their performance, and continuously improve through a standardized evaluation framework.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Mandoline
It helps by enabling LLMs to self-evaluate using the Model Context Protocol (MCP), define custom evaluation metrics, score prompt and response pairs, and learn from historical results, fostering continuous performance enhancement.
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.