MCP Server Architecture Patterns for LLM-Integrated Applications
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to external tools, data sources, and services. Within months of release, hundreds of community-built MCP servers appeared on GitHub, but no software-maintenance literature has yet described how the ecosystem is being structured in production. This industry experience paper catalogues five recurring MCP server architectural patterns observed across an enumerated corpus of fifteen independently developed servers (five production servers from the ANSYR voice AI platform plus ten public servers from the official MCP registry): Resource Gateway, Tool Orchestrator, Stateful Session Server, Proxy Aggregator, and Domain-Specific Adapter. Each pattern is described in the structured form of Gamma et al.: context, problem, solution, and consequences. We also document four anti-patterns and a set of cross-cutting concerns around authentication, versioning, and observability. The quantitative evaluation contributes three measurements: inter-rater reliability of the taxonomy across two independent LLM raters on 54 held-out servers (Cohen's kappa = 0.76), which also localizes three pattern-boundary ambiguities; transport overhead measured end-to-end on loopback and modeled for cross-host paths; and a tool-count study showing tool-selection accuracy drops below 90% between 10 and 15 tools per context for Claude Haiku 4.5 and between 20 and 30 tools for Sonnet 4. Code, corpus, and prompts are released as a replication package.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Valencer: an API to Query Valence Patterns in FrameNet
This paper introduces Valencer: a RESTful API to search for annotated sentences matching a given combination of syntactic realizations of the arguments of a predicate {--} also called {`}valence pattern{'} {--} in the Fr…
Question AnsweringGarfield: System Support for Byzantine Machine Learning
We present Garfield, a library to transparently make machine learning (ML) applications, initially built with popular (but fragile) frameworks, e.g., TensorFlow and PyTorch, Byzantine-resilient. Garfield relies on a nove…
BIG-bench Machine LearningBag-of-Features Image Indexing and Classification in Microsoft SQL Server Relational Database
This paper presents a novel relational database architecture aimed to visual objects classification and retrieval. The framework is based on the bag-of-features image representation model combined with the Support Vector…
ClassificationGeneral ClassificationRetrievalVEDLIoT -- Next generation accelerated AIoT systems and applications
The VEDLIoT project aims to develop energy-efficient Deep Learning methodologies for distributed Artificial Intelligence of Things (AIoT) applications. During our project, we propose a holistic approach that focuses on o…
TOMAAT: volumetric medical image analysis as a cloud service
Deep learning has been recently applied to a multitude of computer vision and medical image analysis problems. Although recent research efforts have improved the state of the art, most of the methods cannot be easily acc…
Deep LearningMedical Image Analysis