MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models

TL;DR

MCPEval is an open-source framework that automates comprehensive evaluation of AI agents based on Large Language Models, addressing limitations of static benchmarks and manual data collection.

Contribution

It introduces a novel MCP-based framework that automates task generation, standardizes metrics, and integrates with native tools for scalable LLM agent evaluation.

Findings

Effective in revealing nuanced, domain-specific performance

Automates end-to-end evaluation process

Standardizes metrics across diverse domains

Abstract

The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks and labor-intensive data collection, limiting practical assessment. We introduce MCPEval, an open-source Model Context Protocol (MCP)-based framework that automates end-to-end task generation and deep evaluation of LLM agents across diverse domains. MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines. Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance. We publicly release MCPEval https://github.com/SalesforceAIResearch/MCPEval to promote reproducible and standardized LLM agent evaluation.