Evalbench
Verified IntegrationClient Configuration
— Connect Evalbench to Claude Desktop or Cursor in seconds{
"mcpServers": {
"evalbench": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-evalbench"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides an offline LLM and agent evaluation harness with regression gates, integrating seamlessly into CI/CD workflows.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Evalbench
Evalbench is an offline evaluation harness for Large Language Models (LLMs) and AI agents. It features regression gates and is designed for seamless integration into CI/CD workflows to ensure agent quality.
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.