MCP Server Architecture Patterns for LLM-Integrated Applications

• URL: http://arxiv.org/abs/2606.30317v1
• Date: Mon, 29 Jun 2026 13:59:41 GMT
• Title: MCP Server Architecture Patterns for LLM-Integrated Applications
• Abstract summary: The Model Context Protocol (MCP) defines a standardized interface for connecting large language models to external tools, data sources, and services.<n>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.<n>This paper catalogues five recurring MCP server architectural patterns observed across an enumerated corpus of fifteen independently developed servers.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Joint Optimization of Tool Creation and Use for Large Language Model Agents [69.07066297088187]
  SMITH (-grounded Multi-task Iterative Tool Honing) trains tool creation and tool use inside a single policy.<n>A 4B Qwen3 trained with SMITH on 13 procedural reasoning tasks with exact verifiers reaches 79.8 macro-average accuracy on held-out tasks.<n>It also reaches 40.4 on TabMWP-Hard and 42.6 on out-of-domain GQA (+7.6 over the best same-backbone inference-time baseline)
  arXiv  Detail & Related papers  (2026-08-25T13:59:34Z)
• Code2UML: Agentic LLMs with context engineering for scalable software visualization [7.069738194755401]
  This paper introduces an agentic architecture with context engineering for automated diagram generation from source code repositories.<n>It employs a hierarchy of five specialized agents: PlannerAgent, Analyzer DiagramAgent, CorrectorAgent and DependencyAnalyzerAgent, built on the Claude Agent SDK.<n>A deterministic, importance-weighted IR compaction layer transforms full project IRs into diagram-specific views guaranteed to fit within token constraints.
  arXiv  Detail & Related papers  (2026-05-23T08:01:26Z)
• TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments [0.0]
  Production agent frameworks transmit tool schemas as MCP, a format designed for machine parsing, not for interpretation by language models.<n>For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production sizes.<n>We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary.
  arXiv  Detail & Related papers  (2026-05-04T15:35:45Z)
• OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce [68.7552227901176]
  OneMall is an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou.<n>It unifies the e-commerce's multiple item distribution scenarios, such as Product-card, short-video and live-streaming.<n>OneMall has been deployed, serving over 400 million daily active users at Kuaishou.
  arXiv  Detail & Related papers  (2026-01-29T14:22:39Z)
• HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions [50.61510609116118]
  HuggingR$4$ is a novel framework that combines Reasoning, Retrieval, Refinement, and Reflection to efficiently select models.<n>It attains a workability rate of 92.03% and a reasonability rate of 82.46%, surpassing existing method by 26.51% and 33.25% respectively.
  arXiv  Detail & Related papers  (2025-11-24T03:13:45Z)
• LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System [55.33058620876928]
  LLM x MapReduce-V3 is a hierarchically modular agent system for long-form survey generation.<n>System captures research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey.<n>Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length.
  arXiv  Detail & Related papers  (2025-10-13T01:38:37Z)
• MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers [86.00932417210477]
  We introduce MCP-Universe, the first comprehensive benchmark specifically designed to evaluate LLMs in realistic and hard tasks through interaction with real-world MCP servers.<n>Our benchmark encompasses 6 core domains spanning 11 different MCP servers: Location Navigation, Repository Management, Financial Analysis, 3D Design, Browser Automation, and Web Searching.<n>We find that even SOTA models such as GPT-5 (43.72%), Grok-4 (33.33%) and Claude-4.0-Sonnet (29.44%) exhibit significant performance limitations.
  arXiv  Detail & Related papers  (2025-08-20T13:28:58Z)
• Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks [3.3705400036304205]
  "Semantic drift" compromises data and governance, and impairs the utility of services like text-to-RAG.<n>This paper proposes a novel framework for the automated extraction of fine-grained schema lineage from multilingual enterprise pipeline scripts.<n>Result: A 32B open-source model, using a single reasoning trace, can achieve performance comparable to the GPT series under standard prompting.
  arXiv  Detail & Related papers  (2025-08-10T05:04:32Z)
• LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools? [50.60770039016318]
  We present LiveMCPBench, the first comprehensive benchmark for benchmarking Model Context Protocol (MCP) agents.<n>LiveMCPBench consists of 95 real-world tasks grounded in the MCP ecosystem.<n>Our evaluation covers 10 leading models, with the best-performing model reaching a 78.95% success rate.
  arXiv  Detail & Related papers  (2025-08-03T14:36:42Z)
• Making REST APIs Agent-Ready: From OpenAPI to MCP Servers for Tool-Augmented LLMs [0.0]
  We present AutoMCP, a compiler that generates MCP servers from OpenAPI 2.0/3.0 specifications.<n>We evaluate AutoMCP on 50 real-world APIs spanning 5,066 endpoints across over 10 domains.
  arXiv  Detail & Related papers  (2025-07-21T20:20:31Z)
• A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis [8.943261888363622]
  We introduce MCPCorpus, a large-scale dataset containing around 14K MCP servers and 300 MCP clients.<n>Each artifact is annotated with 20+ normalized attributes capturing its identity, interface configuration, GitHub activity, and metadata.<n> MCPCorpus provides a reproducible snapshot of the real-world MCP ecosystem, enabling studies of adoption trends, ecosystem health, and implementation diversity.
  arXiv  Detail & Related papers  (2025-06-30T02:37:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.