Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910264801099776 |
|---|---|
| author | Pujara, Aditya Zhu, Xiaogang Chen, Hsiang-Ting |
| author_facet | Pujara, Aditya Zhu, Xiaogang Chen, Hsiang-Ting |
| contents | The rapid development of LLMs coupled with the introduction of Model Context Protocol (MCP) has revolutionized how intelligent agents interact with APIs through deterministic and structured methods \cite{ModelContextProtocolIntro2025}. While some existing systems like AutoMCP attempt to automate a previously completely manual process of generating MCP servers, they fail to address the recurring challenge of maintaining synchronization between evolving enterprise-level APIs and their corresponding MCP toolset implementation \cite{mastouri2025makingrestapisagentready}. This paper introduces DeltaMCP, a specification-aware, incremental regeneration tool for enterprise-grade MCP servers. DeltaMCP enables developers to only update the affected tooling of MCP servers, given a new release of it's corresponding service's OpenAPI specification. Using Azure REST API specifications as the evaluation dataset, DeltaMCP is benchmarked against baseline full generation methods on generation quality and system performance. The results demonstrate the reduction in developer overhead through DeltaMCP whilst improving maintainability and version consistency. This research offers a scalable approach for enterprises seeking to maintain high-fidelity, up-to-date MCP server infrastructures for LLM-based systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28148 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers Pujara, Aditya Zhu, Xiaogang Chen, Hsiang-Ting Software Engineering Artificial Intelligence The rapid development of LLMs coupled with the introduction of Model Context Protocol (MCP) has revolutionized how intelligent agents interact with APIs through deterministic and structured methods \cite{ModelContextProtocolIntro2025}. While some existing systems like AutoMCP attempt to automate a previously completely manual process of generating MCP servers, they fail to address the recurring challenge of maintaining synchronization between evolving enterprise-level APIs and their corresponding MCP toolset implementation \cite{mastouri2025makingrestapisagentready}. This paper introduces DeltaMCP, a specification-aware, incremental regeneration tool for enterprise-grade MCP servers. DeltaMCP enables developers to only update the affected tooling of MCP servers, given a new release of it's corresponding service's OpenAPI specification. Using Azure REST API specifications as the evaluation dataset, DeltaMCP is benchmarked against baseline full generation methods on generation quality and system performance. The results demonstrate the reduction in developer overhead through DeltaMCP whilst improving maintainability and version consistency. This research offers a scalable approach for enterprises seeking to maintain high-fidelity, up-to-date MCP server infrastructures for LLM-based systems. |
| title | DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28148 |