Model Context Protocol adoption grows fast across research and GitHub repositories
A Two-Dimensional Study of the Model Context Protocol: Publication and Adoption
Software Engineering
Summary
Connecting large language models to external tools and data is complicated, so Anthropic created the Model Context Protocol (MCP) to standardize this interaction. The authors studied both scientific papers and software projects using MCP over time. They found that research papers and GitHub projects using MCP grew quickly together in early 2025 and peaked in early 2026. Most projects use MCP to enable other applications rather than directly working on improving or securing it. The study also categorizes how MCP is being used across different fields and suggests directions for future work.
What this means in practice
- •For software development teams: Identify how MCP can enable integration of language models with external tools in different product areas based on real-world usage patterns.
- •For open-source project managers: Track trends in MCP adoption to guide decisions about choosing protocols for large language model interoperability in community projects.
A survey. It maps existing work.
Authors
Natarajan Chidambaram, Mauro Dalle Lucca Tosi, Jordi Cabot
Abstract
The Model Context Protocol (MCP), released by Anthropic in November 2024, standardizes how large language model applications connect to external tools and data sources. Despite MCP's rapid growth, no study has jointly characterized its emergence in the research literature, its adoption on GitHub and the relationship between them. We address this gap with a longitudinal, two-dimensional study of 802 MCP-related publications and 33,319 GitHub repositories. We characterize their growth and identify their application domains via BERTopic and usage contexts via a human-validated GPT-5.6-Luna classifier. We find that publications and repositories began rapid growth within a month of each other in 2025, and peaked together in March 2026. Notably, a second growth wave alone accounts for 49.5% of the GitHub repositories. Most publications (57.8%) and nearly all repositories (93.7%) use MCP as an enabling technology rather than for analyzing, evaluating, extending, or securing it directly. Among repositories, the latter category concentrates almost entirely in one general-purpose topic, while applied usage spreads into product-specific niches. Finally, we provide an overview of the MCP landscape and recommendations to researchers and practitioners in this field.