Dataset links MCP servers consumers and development activity across projects
MCP-Eco: A Linked Dataset of MCP Servers, Consumers, and Development Activity
Software Engineering
Summary
Managing how language models connect to external tools and data is complicated because the information is scattered in many places. The authors created a big dataset called MCP-Eco that brings together details about these connections, the software projects that use them, and their coding history. This dataset helps people study and improve how these connections work and lets programmers see existing configurations and tool details in one place.
What this means in practice
- •For software developers: Inspect and reuse existing MCP tool configurations and server interfaces to improve model integration in applications.
- •For software project managers: Track development activities and dependencies across MCP-related projects to aid in maintenance and coordination.
Authors
Khalid Tounoussi, Mohammed Sayagh, Ali Ouni, Yutaro Kashiwa
Abstract
The Model Context Protocol (MCP) enables LLM agents to access external tools and data. Studying its software ecosystem requires connecting server interfaces, the projects that configure these servers, and their development activity. However, this information is scattered across directories, package registries, configuration files, and repository histories. We present MCP-Eco, a relational dataset that integrates these sources and links consumer configuration declarations to candidate server projects. Its frozen release contains 16,880,899 records across 19 Parquet tables, covering 78,302 candidate server projects, 16,165 candidate consuming repositories, and 9,200 configuration declarations. Of these declarations, 5,975 resolve to 5,138 distinct repository-server pairs. The dataset also includes tool, resource, and prompt descriptions, declared dependencies, and associated development records, including pull requests, reviews, issues, and commits. Provenance fields distinguish directory-reported capabilities from those observed through live probing and document discovery sources and declaration-matching methods. These connections support research on MCP interface design, configuration practices, and repository maintenance, while enabling practitioners to inspect tool schemas and existing integration configurations. The dataset and accompanying analysis scripts are publicly available at https://huggingface.co/datasets/mcp-research-alliance/mcp-ecosystem Demo video: https://www.youtube.com/watch?v=N7TqnNneSfU