Evaluating Tool Cloning in Agentic-AI Ecosystems

• URL: http://arxiv.org/abs/2605.09817v2
• Date: Sun, 17 May 2026 00:18:32 GMT
• Title: Evaluating Tool Cloning in Agentic-AI Ecosystems
• Abstract summary: This study is the first large-scale measurement study of tool cloning in agentic AI ecosystems.<n>It covers 7,508 Model Context Protocol (MCP) repositories with 87,564 extracted tools and 1,353 Skills repositories with 12,447 tools, for a total of 8,861 repositories and 100,011 tool entries.
• Score: 7.733750839250171
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distributed through public marketplaces, raw tool counts may substantially overstate ecosystem diversity if many repositories are cloned, lightly modified, or derived from shared templates. Such hidden duplication can contaminate benchmark splits, propagate vulnerable implementations, bias measurements of tool-use generalization, and raise provenance, attribution, and intellectual-property concerns. We present, to our knowledge, the first large-scale measurement study of tool cloning in agentic AI ecosystems. We curate a unified dataset from multiple public platforms, covering 7,508 Model Context Protocol (MCP) repositories with 87,564 extracted tools and 1,353 Skills repositories with 12,447 tools, for a total of 8,861 repositories and 100,011 tool entries. To measure implementation-level duplication, we build a repository-level auditing pipeline using complementary lexical and fuzzy-structural similarity metrics, and compute pairwise similarity across MCP-to-MCP, Skills-to-Skills, and MCP-to-Skills repository pairs. We further manually verify 100 sampled pairs per MCP and Skills ecosystem across similarity-score buckets to calibrate how often high similarity reflects true code cloning. Our analysis shows that cloning is not an isolated artifact: high-similarity regions appear across comparison settings, and 60\% of high-Jaccard candidates and 85\% of high-ssdeep candidates in the MCP ecosystem are manually verified as clones. These results indicate that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems. They further suggest that agent-tool datasets and benchmarks should account for repository provenance and implementation similarity when measuring tool diversity or constructing evaluation splits.

Related papers

• DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents [77.19284650368924]
  We present DianShi-RxnDB, a large-scale, fine-grained organic reaction data platform.<n>It is built via a fully automated extraction and normalization pipeline.<n>The platform provides a Web research workbench for searching, filtering, comparing, and source-verifying records.
  arXiv  Detail & Related papers  (2026-09-06T16:20:43Z)
• Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation [1.6774701449274187]
  Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge.<n>The Model Context Protocol (MCP) standardizes how such tools are surfaced, and a proxy MCP server aggregates many backend servers behind a single endpoint.<n>We present SCOUT, which reframes tool exposure as a context-selection problem, injecting only tools relevant to the current step.
  arXiv  Detail & Related papers  (2026-08-25T02:33:44Z)
• A Large-Scale Dataset of MCP Implementations on GitHub [7.0349768355860895]
  The Model Context Protocol (MCP) has introduced a new standard for connecting large language models to external tools and services.<n>This study presents the first large-scale, evidence-based dataset of real-world MCP implementation collected directly from GitHub.
  arXiv  Detail & Related papers  (2026-07-11T05:08:32Z)
• SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents [64.59100414726556]
  Large language model (LLM) agents increasingly rely on harnesses that manage context, tools, and multi-turn execution.<n>Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods fail to align isolated tool descriptions with the agent's true task intention.<n>We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns.
  arXiv  Detail & Related papers  (2026-06-15T11:37:37Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation [7.907933839674293]
  Large Language Models (LLMs) have emerged as capable coding assistants that operate over larges through either agentic exploration or full-context generation.<n>We introduce ReCUBE, a benchmark in which LLMs reconstruct a masked file within a real-world repository, using all remaining source files, dependency specifications, and documentation as their only source of context.<n>We propose the Caller-Centric Exploration (CCE) toolkit, a set of dependency graph-based tools that can be integrated into agentic frameworks.
  arXiv  Detail & Related papers  (2026-03-26T08:04:15Z)
• Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
  Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:43:03Z)
• ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents [31.77712252239516]
  Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents.<n>There is a lack of systematic and reliable evaluation benchmarks for PRMs in tool-using settings.<n>We introduce ToolPRMBench, a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents.
  arXiv  Detail & Related papers  (2026-01-18T07:48:36Z)
• A Large Scale Empirical Analysis on the Adherence Gap between Standards and Tools in SBOM [54.38424417079265]
  A Software Bill of Materials (SBOM) is a machine-readable artifact that organizes software information.<n>Following standards, organizations have developed tools for generating and utilizing SBOMs.<n>This paper presents the first large-scale, two-stage empirical analysis of the adherence gap, using our automated evaluation framework, SAP.
  arXiv  Detail & Related papers  (2026-01-09T08:26:05Z)
• ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning [80.10274552177096]
  Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks.<n>The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools.<n>We propose a systematic approach to automatically an unstructured collection of tools into a structured tool library.
  arXiv  Detail & Related papers  (2025-10-09T04:11:16Z)
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
  This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
  arXiv  Detail & Related papers  (2025-08-13T19:14:48Z)
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models [76.72220653705679]
  We introduce MCPEval, an open-source framework that automates end-to-end task generation and deep evaluation of intelligent agents.<n> MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines.<n> Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance.
  arXiv  Detail & Related papers  (2025-07-17T05:46:27Z)
• MCP-Zero: Active Tool Discovery for Autonomous LLM Agents [13.005899769943442]
  We introduce MCP-Zero, an active agent framework that restores tool discovery autonomy to LLMs themselves.<n>Instead of overwhelming models with all available tools, MCP-Zero enables agents to actively identify capability gaps, and request specific tools on-demand.<n>We construct MCP-tools, a comprehensive dataset of 308 MCP servers and 2,797 tools from the official Model-Context-Protocol repository.
  arXiv  Detail & Related papers  (2025-06-01T15:48:53Z)
• T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search [51.91311158085973]
  multimodal misinformation often arises from mixed forgery sources, requiring dynamic reasoning and adaptive verification.<n>We propose T2Agent, a novel misinformation detection agent that incorporates a toolkit with Monte Carlo Tree Search.<n>Extensive experiments show that T2Agent consistently outperforms existing baselines on challenging mixed-source multimodal misinformation benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T09:50:55Z)
• Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation [15.461189659020187]
  Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies. We introduce ToolGen, an approach that integrates autocompletion tools into the code LLM generation process to address these dependencies. ToolGen comprises two main phases: Trigger Insertion and Model Fine-tuning (Offline), and Tool-integrated Code Generation (Online)
  arXiv  Detail & Related papers  (2024-01-12T06:03:56Z)
• Repo2Vec: A Comprehensive Embedding Approach for Determining Repository Similarity [2.095199622772379]
  Repo2Vec is a comprehensive embedding approach to represent a repository as a distributed vector. We evaluate our method with two real datasets from GitHub for a combined 1013 repositories.
  arXiv  Detail & Related papers  (2021-07-11T18:57:03Z)

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.