Code2MCP: Transforming Code Repositories into MCP Services
Chaoqian Ouyang, Ling Yue, Shimin Di, Libin Zheng, Linan Yue, Shaowu Pan, Jian Yin, Min-Ling Zhang
摘要
The Model Context Protocol (MCP) aims to create a standard for how Large Language Models use tools. However, most current research focuses on selecting tools from an existing pool. A more fundamental, yet largely overlooked, problem is how to populate this pool by converting the vast number of existing software projects into MCP-compatible services. To bridge this gap, we introduce Code2MCP, an agent-based framework that automatically transforms a GitHub repository into a functional MCP service with minimal human intervention. Code2MCP employs a multi-agent workflow for code analysis, environment setup, tool function design, and service generation, enhanced by a self-correcting loop to ensure reliability. We demonstrate that Code2MCP successfully transforms open-source computing libraries in scientific fields such as bioinformatics, mathematics, and fluid dynamics that are not available in existing MCP servers. By providing a novel automated pathway to unlock GitHub, the world's largest code repository, for the MCP ecosystem, Code2MCP serves as a catalyst to significantly accelerate the protocol's adoption and practical application. The code is public at https://anonymous.4open.science/r/code2mcp-7E34.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- CoS: Towards Optimal Event Scheduling via Chain-of-SchedulingYiming Zhao, Jiwei Tang, Shimin Di, Libin Zheng 等AAAI 2026 · 被引用 7 次
- SpatialJB: How Text Distribution Art Becomes The "Jailbreak Key" for LLM GuardrailsZhiyi Mou, Jingyuan Yang, ZEHENG QIAN, Wangze Ni 等ICML 2026 · 被引用 1 次
它引用的顶会 Paper9
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu 等NeurIPS 2023 · 被引用 5,989 次
- SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao 等ICLR 2024 · 被引用 2,082 次
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris 等UIST 2023 · 被引用 1,882 次
- HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li 等NeurIPS 2023 · 被引用 1,778 次
- Gorilla: Large Language Model Connected with Massive APIsShishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. GonzalezNeurIPS 2024 · 被引用 1,715 次
相关 Paper
- MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP ToolsWenhao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen 等ACL 2026 · 被引用 8 次
- MCP-Focus: Leveraging Function-Oriented Document Enhancement for MCP Server RetrievalWenchun Jing, Haiyang Shen, Haoran Wang, Qi Liu 等SIGIR 2026
- MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated ToolsZikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong 等AAAI 2026 · 被引用 19 次
- MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP ServersZhenting Wang, Qi Chang, Hemani Patel, Shashank Biju 等ICLR 2026 · 被引用 109 次
- AgentBound: Securing Execution Boundaries of AI AgentsChristoph Bühler, Matteo Biagiola, Luca Di Grazia, Guido SalvaneschiFSE 2026 · 被引用 1 次
