MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Mengying, Chen, Pei, Hong, Geng, An, Baichao, Chen, Jinsong, Wan, Binwang, Pan, Xudong, Dai, Jiarun, Yang, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911339896635392
author Wu, Mengying
Chen, Pei
Hong, Geng
An, Baichao
Chen, Jinsong
Wan, Binwang
Pan, Xudong
Dai, Jiarun
Yang, Min
author_facet Wu, Mengying
Chen, Pei
Hong, Geng
An, Baichao
Chen, Jinsong
Wan, Binwang
Pan, Xudong
Dai, Jiarun
Yang, Min
contents Model Context Protocol (MCP) enables agents to interact with external tools, yet empirical research on MCP is hindered by the lack of large-scale, accessible datasets. We present MCPZoo, the largest and most comprehensive dataset of MCP servers collected from multiple public sources, comprising 129,059 servers (56,053 distinct). MCPZoo includes 16,356 server instances that have been deployed and verified as runnable and interactable, supporting realistic experimentation beyond static analysis. The dataset provides unified metadata and access interfaces, enabling systematic exploration and interaction without manual deployment effort. MCPZoo is released as an open and accessible resource to support research on MCP-based systems and security analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15144
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent
Wu, Mengying
Chen, Pei
Hong, Geng
An, Baichao
Chen, Jinsong
Wan, Binwang
Pan, Xudong
Dai, Jiarun
Yang, Min
Cryptography and Security
Model Context Protocol (MCP) enables agents to interact with external tools, yet empirical research on MCP is hindered by the lack of large-scale, accessible datasets. We present MCPZoo, the largest and most comprehensive dataset of MCP servers collected from multiple public sources, comprising 129,059 servers (56,053 distinct). MCPZoo includes 16,356 server instances that have been deployed and verified as runnable and interactable, supporting realistic experimentation beyond static analysis. The dataset provides unified metadata and access interfaces, enabling systematic exploration and interaction without manual deployment effort. MCPZoo is released as an open and accessible resource to support research on MCP-based systems and security analysis.
title MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent
topic Cryptography and Security
url https://arxiv.org/abs/2512.15144