Search papers, labs, and topics across Lattice.
ToolRosetta automates the conversion of open-source code repositories into Model Context Protocol (MCP)-compatible tools usable by LLMs, addressing the scalability bottleneck of manual tool standardization. It autonomously plans toolchains, identifies relevant codebases, converts them into executable MCP services, and incorporates a security inspection layer. Experiments across scientific domains show ToolRosetta improves task completion performance by leveraging specialized open-source tools, outperforming commercial LLMs and existing agent systems.
Automating the messy process of turning open-source code into LLM tools unlocks a new level of agent capabilities, outperforming even commercial LLMs.
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.
