TheMCPCompany: Creating General-purpose Agents with Task-specific Tools

TL;DR

The paper introduces TheMCPCompany, a benchmark for evaluating large language model agents using task-specific tools via MCP, highlighting current capabilities and challenges in complex real-world environments.

Contribution

It presents a new benchmark with over 18,000 tools for evaluating tool-calling agents and analyzes their performance in complex, real-world tasks.

Findings

Tool-calling agents can outperform browser-based agents with perfect tool retrieval.

Smaller models struggle to utilize large tool sets effectively.

GPT-5 performs close to ground-truth tools in complex environments.

Abstract

Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web browsers, while being easier to develop and maintain than GUIs. However, current general-purpose agents predominantly rely on web browsers for interacting with the environment. Here, we introduce TheMCPCompany, a benchmark for evaluating tool-calling agents on tasks that involve interacting with various real-world services. We use the REST APIs of these services to create MCP servers, which include over 18,000 tools. We also provide manually annotated ground-truth tools for each task. In our experiments, we use the ground truth tools to show the potential of tool-calling agents for both improving performance and reducing costs assuming perfect tool retrieval. Next, we explore agent performance using tool retrieval to study the real-world practicality of tool-based agents. While all models with tool retrieval perform similarly or better than browser-based agents, smaller models cannot take full advantage of the available tools through retrieval. On the other hand, GPT-5's performance with tool retrieval is very close to its performance with ground-truth tools. Overall, our work shows that the most advanced reasoning models are effective at discovering tools in simpler environments, but seriously struggle with navigating complex enterprise environments. TheMCPCompany reveals that navigating tens of thousands of tools and combining them in non-trivial ways to solve complex problems is still a challenging task for current models and requires both better reasoning and better retrieval models.