Code2MCP: A Multi-Agent Framework for Automated Transformation of Code Repositories into Model Context Protocol Services

2025-09-07

AI Summary

The “N×M” adaptation challenge—where each large language model (LLM) must be manually integrated with each tool—hinders scalable tool interoperability in the LLM ecosystem. Method: This paper proposes an LLM-driven automation framework that converts arbitrary GitHub repositories into Model Context Protocol (MCP)-compliant services in a single step. It employs a multi-agent collaborative closed-loop pipeline—comprising execution, review, and repair—integrating static code analysis, automated environment provisioning, service-oriented deployment pipelines, and LLM-assisted debugging. Contribution/Results: To our knowledge, this is the first systematic solution bridging raw open-source code to production-ready MCP services—the “last-mile” gap. The framework fully automates conversion, generating standardized MCP service interfaces and comprehensive technical documentation. The implementation is open-sourced, drastically reducing manual adaptation effort and accelerating large-scale MCP ecosystem adoption.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Multiagent Systems: Adversarial Agents

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The proliferation of Large Language Models (LLMs) has created a significant integration challenge in the AI agent ecosystem, often called the "$N imes M$ problem," where N models require custom integrations for M tools. This fragmentation stifles innovation and creates substantial development overhead. While the Model Context Protocol (MCP) has emerged as a standard to resolve this, its adoption is hindered by the manual effort required to convert the vast universe of existing software into MCP-compliant services. This is especially true for the millions of open-source repositories on GitHub, the world's largest collection of functional code. This paper introduces Code2MCP, a highly automated, agentic framework designed to transform any GitHub repository into a functional MCP service with minimal human intervention. Our system employs a multi-stage workflow that automates the entire process, from code analysis and environment configuration to service generation and deployment. A key innovation of our framework is an LLM-driven, closed-loop "Run--Review--Fix" cycle, which enables the system to autonomously debug and repair the code it generates. Code2MCP produces not only deployable services but also comprehensive technical documentation, acting as a catalyst to accelerate the MCP ecosystem by systematically unlocking the world's largest open-source code repository and automating the critical last mile of tool integration. The code is open-sourced at https://github.com/DEFENSE-SEU/MCP-Github-Agent.

Problem

• Automates conversion of GitHub repositories into MCP services
• Solves N×M integration problem between LLMs and tools
• Reduces manual effort in creating Model Context Protocol services

Innovation

• Automated transformation of GitHub repositories into MCP services
• Multi-stage workflow with LLM-driven closed-loop debugging cycle
• Generates deployable services and comprehensive technical documentation