MCP Server Dataset Builder logo

MCP Server Dataset Builder

by wanghaisheng

A tool for building and maintaining a dataset of Model Context Protocol (MCP) servers. It automatically collects, categorizes, and updates information about MCP servers from multiple sources.

View on GitHub

Last updated: N/A

What is MCP Server Dataset Builder?

The MCP Server Dataset Builder is a tool designed to extract, categorize, and maintain a dataset of Model Context Protocol (MCP) servers. It aggregates data from curated lists and GitHub searches to provide a comprehensive view of the MCP server ecosystem.

How to use MCP Server Dataset Builder?

The dataset is automatically updated daily via GitHub Actions. For manual triggering, navigate to the 'Actions' tab, select 'Unified MCP Servers Extraction', and click 'Run workflow'. Local development requires installing dependencies and running extraction scripts.

Key features of MCP Server Dataset Builder

  • Dual Data Sources

  • Automatic Categorization

  • Tech Stack Detection

  • Emoji Tagging

  • Daily Updates

  • Data Persistence

Use cases of MCP Server Dataset Builder

  • Analyzing the MCP server landscape

  • Tracking the adoption of different technologies

  • Identifying popular MCP server implementations

  • Building tools and services around MCP servers

FAQ from MCP Server Dataset Builder

What data sources are used?

The tool uses the awesome-mcp-servers repository and GitHub search.

How is data categorized?

Repositories are categorized based on their content and purpose (e.g., Framework, Utility, Client).

What technologies are detected?

The tool identifies languages (Python, TypeScript, Go), frameworks (FastAPI, Langchain, Spring), protocols (SSE, WebSocket, HTTP), deployment methods (Cloud, Local, Docker), and platforms (iOS, Windows, Linux).

How often is the dataset updated?

The dataset is automatically updated daily.

Can I contribute to the project?

Yes, contributions are welcome! Please submit a Pull Request.