I Built a Live Registry of 750+ MCP Servers — Here's What I Found

I Built a Live Registry of 750+ MCP Servers — Here’s What I Found

我构建了一个包含 750 多个 MCP 服务器的实时注册表——以下是我的发现

Model Context Protocol (MCP) has exploded in the past six months. Every week, dozens of new MCP servers appear on GitHub — tools that let Claude and other AI assistants connect to databases, APIs, file systems, and basically anything else you can imagine. The problem? There’s no easy way to discover them. So I built one: kiprio.com/mcp-registry — a live registry that tracks, categorises, and ranks MCP servers from across GitHub and community lists. Here’s what I found after indexing 750+ servers.

模型上下文协议(MCP)在过去六个月中呈爆炸式增长。每周都有数十个新的 MCP 服务器出现在 GitHub 上——这些工具让 Claude 和其他 AI 助手能够连接到数据库、API、文件系统以及你能想象到的几乎任何事物。问题在于,目前还没有简单的方法来发现它们。因此,我构建了一个注册表:kiprio.com/mcp-registry —— 这是一个实时注册表,用于跟踪、分类和排名来自 GitHub 和社区列表的 MCP 服务器。在索引了 750 多个服务器后,以下是我的发现。

The MCP Ecosystem by Numbers

MCP 生态系统数据概览

  • 750+ servers indexed (and growing — the tracker runs daily)

  • Language breakdown:

    • Python: 32% (241 servers)
    • TypeScript: 31% (236 servers)
    • JavaScript: 9% (66 servers)
    • Go: 8% (59 servers)
    • Rust: 4% (30 servers)
  • 已索引 750 多个服务器(且数量还在增长——跟踪器每天运行)

  • 语言分布:

    • Python:32% (241 个服务器)
    • TypeScript:31% (236 个服务器)
    • JavaScript:9% (66 个服务器)
    • Go:8% (59 个服务器)
    • Rust:4% (30 个服务器)

The Python/TypeScript split is almost even. Python dominates for data-heavy integrations (databases, analytics, ML). TypeScript leads for browser-based and web service integrations.

Python 和 TypeScript 的占比几乎持平。Python 在数据密集型集成(数据库、分析、机器学习)方面占据主导地位;而 TypeScript 在基于浏览器和 Web 服务的集成方面处于领先地位。

Stars distribution: The median MCP server has under 50 stars. Most are small personal projects. But the top 10% have thousands — these are the tools that solve real problems and get shared.

星标分布: 中位数的 MCP 服务器星标数不到 50 个。大多数是小型个人项目。但排名前 10% 的项目拥有数千个星标——这些是真正解决问题并被广泛分享的工具。

Most-starred categories:

  • Developer tools (Claude Code enhancers, terminal integrations)
  • Workflow automation (n8n, custom pipeline builders)
  • Database connectors (PostgreSQL, SQLite, Redis)
  • API integrations (GitHub, Slack, Notion, Linear)
  • File system and search tools

星标最多的类别:

  • 开发者工具(Claude Code 增强器、终端集成)
  • 工作流自动化(n8n、自定义流水线构建器)
  • 数据库连接器(PostgreSQL、SQLite、Redis)
  • API 集成(GitHub、Slack、Notion、Linear)
  • 文件系统和搜索工具

What’s Actually Useful vs. What’s Hype

哪些真正有用,哪些只是炒作

After looking at 750+ servers, some patterns emerged:

  • The good: Database MCP servers are genuinely useful. Being able to ask “show me the top 10 products by revenue this month” and have Claude query your actual database is compelling. The GitHub MCP server for code review workflows is also solid.
  • The redundant: There are at least 40 different “weather” MCP servers, 30+ “web search” wrappers, and countless “read a file” implementations. The long tail is very long.
  • The interesting: The niche ones. There’s an MCP server for interacting with Betfair betting markets, one for Ethereum on-chain data, one for competitive intelligence monitoring. These solve real specific problems.

在查看了 750 多个服务器后,出现了一些模式:

  • 好的方面: 数据库 MCP 服务器确实非常有用。能够询问“显示本月收入最高的前 10 名产品”,并让 Claude 查询你的实际数据库,这非常有吸引力。用于代码审查工作流的 GitHub MCP 服务器也很扎实。
  • 冗余的方面: 至少有 40 个不同的“天气”MCP 服务器、30 多个“网页搜索”封装器,以及无数个“读取文件”的实现。长尾效应非常明显。
  • 有趣的方面: 一些利基市场的产品。例如,有用于与 Betfair 投注市场交互的 MCP 服务器,有用于以太坊链上数据的服务器,还有用于竞争情报监控的服务器。这些解决了真正具体的问题。

How the Registry Works

注册表的工作原理

The registry scrapes GitHub daily, processes package.json, pyproject.toml, and mcp.json files to confirm these are actual MCP server implementations (not just repos that mention MCP), then ranks them by:

  • GitHub stars (popularity signal)
  • Recent activity (last commit date)
  • Documentation quality (README completeness)
  • Community adoption (dependents, forks)

该注册表每天抓取 GitHub,处理 package.jsonpyproject.tomlmcp.json 文件,以确认它们是实际的 MCP 服务器实现(而不仅仅是提及 MCP 的仓库),然后根据以下指标进行排名:

  • GitHub 星标(流行度信号)
  • 近期活跃度(最后提交日期)
  • 文档质量(README 完整性)
  • 社区采用率(依赖项、分支)

You can search the full registry at kiprio.com/mcp-registry or use the API: 你可以通过 kiprio.com/mcp-registry 搜索完整注册表,或使用 API:

# Search for database MCP servers
curl "https://kiprio.com/v1/mcp-registry/search?q=database"

# Get top-rated servers
curl "https://kiprio.com/v1/mcp-registry/top?limit=20"

# Get server details
curl "https://kiprio.com/v1/mcp-registry/server/modelcontextprotocol/servers"

The API is free with rate limits. For bulk access and webhooks when new servers are added, there’s a Pro tier.

该 API 在速率限制内免费提供。如需批量访问以及在新服务器添加时的 Webhook 通知,我们提供 Pro 层级服务。

The Most Interesting Finding

最有趣的发现

MCP adoption is happening faster than documentation. Most servers work but have minimal README files. The ecosystem is still in “builders building for builders” mode. If you’re writing a new MCP server today, a good README with a working example puts you in the top 20% by documentation quality.

MCP 的采用速度快于文档的完善速度。大多数服务器可以工作,但 README 文件非常简陋。该生态系统仍处于“构建者为构建者构建”的阶段。如果你今天正在编写一个新的 MCP 服务器,一份带有工作示例的优秀 README 文档将使你的文档质量跻身前 20%。

The second interesting finding: TypeScript is winning for production-quality servers. The Python servers tend to be more experimental. The TypeScript ones (especially from the core MCP team and larger contributors) are more complete and battle-tested.

第二个有趣的发现:TypeScript 在生产级服务器方面正在胜出。Python 服务器往往更具实验性。而 TypeScript 服务器(特别是来自核心 MCP 团队和大型贡献者的)更加完整且经过了实战检验。

What’s Next

未来规划

The registry is updated daily. Next additions:

  • Changelog feed: subscribe to get notified when a server you’re watching releases a new version
  • Compatibility matrix: which servers work with which clients (Claude Desktop, Continue.dev, etc.)
  • Quality scores: automated scoring based on test coverage, documentation, activity

注册表每天更新。接下来的新增功能:

  • 更新日志订阅: 当你关注的服务器发布新版本时,订阅以获取通知。
  • 兼容性矩阵: 哪些服务器适用于哪些客户端(Claude Desktop、Continue.dev 等)。
  • 质量评分: 基于测试覆盖率、文档和活跃度的自动评分。

If you’ve built an MCP server and want it indexed, it should be picked up automatically within 24h. If not, submit it here. Built with Python, FastAPI, and a lot of GitHub API calls. The full data is available via the API.

如果你构建了一个 MCP 服务器并希望将其编入索引,它应该会在 24 小时内被自动抓取。如果没有,请在此处提交。该项目使用 Python、FastAPI 和大量的 GitHub API 调用构建。完整数据可通过 API 获取。

— The team at kiprio.com — we build APIs and tools for developers. — kiprio.com 团队 — 我们为开发者构建 API 和工具。