ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization

2026-03-10

AI Summary

This work addresses the lack of standardized interfaces in existing open-source code repositories, which hinders reliable tool invocation by large language models (LLMs) and necessitates extensive human intervention, thereby limiting scalability. To overcome this, we propose ToolRosetta, a framework that achieves the first fully automated translation of open-source tools into the Model Context Protocol (MCP) standard. By integrating LLM-driven autonomous planning, code comprehension, and secure sandboxed execution, ToolRosetta enables agents to automatically identify, encapsulate, and invoke toolchains to accomplish end-to-end tasks. Our approach substantially reduces manual effort, successfully standardizes a wide array of tools across multiple scientific domains, and demonstrates superior task completion rates compared to both existing systems and commercial LLMs.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.

Problem

• tool standardization
• large language models
• open-source repositories
• Model Context Protocol
• code reuse

Innovation

• automated tool standardization
• large language model agents
• Model Context Protocol
• open-source code reuse
• secure tool execution