# From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents

arXiv: https://arxiv.org/abs/2507.16044 · HTML: https://mlsanity.com/paper/2507.16044/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 70 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls](https://mlsanity.com/paper/2402.04253/) (2024)
- [T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step](https://mlsanity.com/paper/2312.14033/) (2023)
- [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025)
- [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025)
- [Understanding the Factors that Impact the Popularity of GitHub Repositories](https://mlsanity.com/paper/1606.04984/) (2016)
- [An Empirical Study on Challenges for LLM Application Developers](https://mlsanity.com/paper/2408.05002/) (2024)
- [LongFuncEval: Measuring the effectiveness of long context models for function calling](https://mlsanity.com/paper/2505.10570/) (2025)
- [A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs](https://mlsanity.com/paper/2411.07098/) (2024)
- [ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentations](https://mlsanity.com/paper/2501.16945/) (2025)
- [Restats: A Test Coverage Tool for RESTful APIs](https://mlsanity.com/paper/2108.08209/) (2021)
- [Collecting Service-Based Maintainability Metrics from RESTful API Descriptions: Static Analysis and Threshold Derivation](https://mlsanity.com/paper/2007.10405/) (2020)

## Built on by (most cited first, 14 of 14)

- [Environment Scaling for Interactive Agentic Experience Collection: A Survey](https://mlsanity.com/paper/2511.09586/) (2025)
- [AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning](https://mlsanity.com/paper/2512.13278/) (2025)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools](https://mlsanity.com/paper/2605.22733/) (2026)
- [SilentProbe: Measuring Silent Failure in Production APIs Used as Agent Tools](https://mlsanity.com/paper/2609.00035/) (2026)
- [Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions](https://mlsanity.com/paper/2609.06792/) (2026)
- [HuggingR4: A Progressive Reasoning Framework for Discovering Optimal Model Companions](https://mlsanity.com/paper/2511.18715/) (2025)
- [Prompt-to-Parts: Generative AI for Physical Assembly and Scalable Instructions](https://mlsanity.com/paper/2512.15743/) (2025)
- [DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent Systems](https://mlsanity.com/paper/2605.05247/) (2026)
- [Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts](https://mlsanity.com/paper/2605.09055/) (2026)
- [Delegating or Doing? Understanding User Behavior in Hybrid Human-Agent Interfaces](https://mlsanity.com/paper/2608.19551/) (2026)
- [A Two-Dimensional Study of the Model Context Protocol: Publication and Adoption](https://mlsanity.com/paper/2609.14721/) (2026)
- [MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents](https://mlsanity.com/paper/2609.24161/) (2026)
- [MCP Error Messages Written for Developers Hurt the Most Capable Agents Most](https://mlsanity.com/paper/2609.35381/) (2026)

## Abstract (arXiv)

The Model Context Protocol (MCP) is emerging as a standard interface through which LLM agents invoke external tools, and a growing ecosystem of MCP servers now mediates access to vendor services. Most of these servers target vendors that already expose REST APIs, yet the relationship between MCP tool interfaces and the underlying API surface has not been empirically characterised. This paper presents the first large-scale study of MCP server construction. We analyse 116 official servers to determine REST reliance and integration strategies (RQ1); examine servers paired with OpenAPI specifications to quantify operation exposure, omission, and mapping patterns (RQ2); evaluate automated generation from 80 real-world OpenAPI contracts (RQ3); and assess specification repair and tool-set transformations to improve correctness and reduce complexity (RQ4). We find that 88.6% of servers are fully or partially REST-backed, with 92% implementing tools as bare API wrappers. MCP servers expose a median of 19% of available operations, following systematic patterns predictable from the specification. Baseline generation succeeds for 76% of sampled tools; automated repair raises this to 94.2%, while filtering and regrouping reduce the median tool count per API by one-third. We release AutoMCP, an end-to-end pipeline integrating specification repair and empirically grounded tool-set transformations.