[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86468-en":3,"doc-seo-86468-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86468,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","A Large-Scale Dataset of MCP Implementations on GitHub","The rapid emergence of the Model Context Protocol (MCP) has introduced a standard for connecting large language models to external tools and services, yet systematic evidence on how MCP is implemented at scale remains limited. This study provides a first large-scale, evidence-based dataset of real-world MCP implementations mined from GitHub. A hybrid REST/GraphQL discovery pipeline identifies 3,238 candidates, then applies multi-stage proof checks to validate 2,297 repositories, tagging operational roles and exporting reproducible JSONL.","A Large-Scale Dataset ofMCP Implementations on GitHub  \nBenny Toeppe  \nOakland University Michigan, USA [btoeppe@oakland.edu](btoeppe@oakland.edu)  \nAmine Barrak  \nOakland University Michigan, USA [aminebarrak@oakland.edu](aminebarrak@oakland.edu)  \nEmna Ksontini  \nUniversity of North Carolina Wilmington North Carolina, USA [ksontinie@uncw.edu](ksontinie@uncw.edu)  \narXiv :2607 . 10 123v 1 [ cs . SE] 11 Jul 2026  \nAbstract  \nThe rapid emergence of the Model Context Protocol (MCP) has introduced a new standard for connecting large language models to external tools and services. Despite its rapid adoption in open-source development, systematic understanding of how MCPis implemented, structured, and maintained remains limited. This study presents the first large-scale, evidence-based dataset of realworld MCP implementation collected directly from GitHub. Using a hybrid pipeline that integrates the GitHub REST and GraphQLAPIs with custom Python verification scripts, 3,238 candidate repositories were discovered, filtered, and validated through multi-stage evidence checks. Each verified project was classified by operational role (e.g., client, server, gateway) and exported in a reproducible JSONL schema. A manual review of a representative subset confirmed an overall precision of 83% at a 95% confidence level, and additionally revealed a set of repositories functioning primarily as educational samples, tutorials, or demonstration templates. A targeted exclusion rule was then applied to remove these non-operational repositories, resulting in a final dataset of 2,297 validated MCP projects. The analysis shows that Python and TypeScript dominate MCP development, with hybrid architectures emerging as the most common design pattern. By emphasizing transparent verification strategies, structured evidence tagging, and reproducible data organization, this work establishes a foundational benchmark for studying real-world MCP ecosystems and supports future research on integration, connectivity, and compatibility across the broader developer community.  \nCCS Concepts  \n• Software and its engineering → Software repositories and source code management; • Information systems → Data mining; • Computing methodologies → Machine learning.  \nKeywords  \nModel Context Protocol (MCP), dataset, GitHub, open source software, repository mining, GraphQL, gateways  \nACM Reference Format:  \nBenny Toeppe, Amine Barrak, and Emna Ksontini. 2026. A Large-Scale Dataset ofMCP Implementations on GitHub. In 23rd International Conference on Mining Software Repositories (MSR’26), April 13–14, 2026, Rio de Janeiro, Brazil. ACM, New York, NY, USA, 5 pages. [https://doi.org/10.1145/3793302](https://doi.org/10.1145/3793302) . 3793311  \nThis work is licensed under a Creative Commons Attribution 4 .0 International License. MSR’26, Rio de Janeiro, Brazil  \n© 2026 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-2474-9/2026/04  \n[https://doi.org/10.1145/3793302.3793311](https://doi.org/10.1145/3793302.3793311)  \n1 Introduction  \nModern language model systems are moving from pure text generation to agents that use tools and live data, enabling them to plan tasks, call external services, and work with information that changes over time rather than relying only on training data [2, 7] . Early attempts to connect LLMs with external tools relied on bespoke, ad hoc solutions such as proprietary function-calling mechanisms and custom API integrations [8, 9] . These proved that models could call external functions but created significant and unsustainable friction for developers, since every new tool or data source required custom integration code that tightly coupled the tool to a specific model or host application [6] . A more scalable approach is to let agents communicate with tools and data sources through a shared protocol. The Model Context Protocol is the most visible effort in this direction. It defines how an application with an embedded model discovers capabiliti","cbCaivVzaucbfZUc","https://ap.wps.com/l/cbCaivVzaucbfZUc","pdf",2425325,4,1,5,"English","en",105,"# Introduction\n## Problem and motivation\n## Dataset construction approach\n## Verification and evidence-based filtering","[{\"question\":\"What problem does the paper address about MCP implementations?\",\"answer\":\"It addresses the lack of a clear, code-grounded understanding of how MCP is implemented at scale and which evidence links repository entries to working client/server behavior.\"},{\"question\":\"How were MCP repositories collected and validated in the study?\",\"answer\":\"The method discovers candidate repositories using GitHub REST and GraphQL APIs, then validates each project through multi-stage evidence checks using code-level signals such as dependency fingerprints and protocol-specific file layouts.\"},{\"question\":\"What is the final dataset size and how are projects organized?\",\"answer\":\"The final dataset contains 2,297 validated MCP projects, classified by operational role (e.g., client, server, gateway) and exported in a reproducible JSONL schema.\"}]",1784211899,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-large-scale-dataset-of-mcp-implementations-on-github","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/a-large-scale-dataset-of-mcp-implementations-on-github/86468/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address about MCP implementations?","Question",{"text":75,"@type":76},"It addresses the lack of a clear, code-grounded understanding of how MCP is implemented at scale and which evidence links repository entries to working client/server behavior.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were MCP repositories collected and validated in the study?",{"text":80,"@type":76},"The method discovers candidate repositories using GitHub REST and GraphQL APIs, then validates each project through multi-stage evidence checks using code-level signals such as dependency fingerprints and protocol-specific file layouts.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the final dataset size and how are projects organized?",{"text":84,"@type":76},"The final dataset contains 2,297 validated MCP projects, classified by operational role (e.g., client, server, gateway) and exported in a reproducible JSONL schema.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":22,"slug":137},19,"General","general"]