mcp.so 每月有 286,704 次造訪,月增率 -3%,定價模式為免費。Scale 每月有 616,915 次造訪,成長率 +12.5%,定價模式為需聯絡報價。
Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.

探索並分享面向 AI 代理與程式開發工具的 Model Context Protocol 伺服器
依名稱、分類、標籤、執行環境或整合查找伺服器,並透過精選、趨勢與最新區塊追蹤社群活躍度。
在接入之前查看託管的 MCP 端點、認證要求以及針對不同客戶端的設定說明。
在專門區塊中發現相容 MCP 的客戶端、官方命令列工具、代理 loops 以及可重複使用的 Claude/Codex 技能。
維護者可發布新伺服器並認領既有條目,讓資訊保持準確且可歸屬。
Scale is an enterprise AI company that supplies the data, evaluation and deployment layers behind production AI. Its Data Engine sources and labels training data for frontier models, its evaluation work benchmarks model capability, and its platform teams help enterprises and governments move AI systems from pilot into real operations.
Human-sourced and expert-annotated training data, including specialist contributors with advanced degrees, at the quality bar frontier labs require.
Public leaderboards plus private benchmarks that test model capability and safety for the most ambitious AI developers.
Platform and services teams that pick the right use case, build the system and take ownership of the outcome.
Agentic systems designed around measurable business outcomes across private equity portfolios, energy and healthcare operations.
專項更強海量的通用 AI 工具目錄,提供更廣泛的軟體探索,但較少專注於特定的 MCP 伺服器。
免費 / 開源為 AI 開發者索引開源代理技能檔案與 MCP 整合的獨立公開目錄。
提供企業級多模態標註與資料管理工具,但較不強調託管式的標註人力。

專項更強在互聯環境中追蹤、評估並交付 AI 模型與代理。

專項更強Focuses on post-deployment LLM observability and evaluation rather than training data generation or annotation.
專項更強Focuses on post-deployment LLM observability and evaluation rather than training data generation or annotation.

專項更強Developer-focused AI tools directory and pricing tracker, though less dedicated to community-contributed MCP server lists.

專項更強將使用者與現成 AI 代理及入門套件連接的市集,但原生的開發者 MCP 工具較少。
專項更強將使用者與現成 AI 代理及入門套件連接的市集,但原生的開發者 MCP 工具較少。

免費 / 開源提供具彈性的開源替代方案,適用於自訂資料標註與真人迴路(Human-in-the-loop)標註管線。