ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization
This addresses the scalability issue in LLM-based tool invocation for developers and researchers by automating tool standardization, though it is incremental as it builds on existing MCP frameworks.
The paper tackles the problem of costly and unreliable reuse of existing code by proposing ToolRosetta, a framework that automatically translates open-source repositories into standardized tools for LLM agents, reducing human effort and improving task completion performance compared to commercial LLMs and existing systems.
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.