mcp-framework
MCP ServerQuantGeekDev/mcp-framework
MCP-Framework is a TypeScript-first toolkit for developing Model Context Protocol (MCP) servers with automatic file-based discovery for tools, resources, and prompts. It streamlines development through a powerful CLI, built-in validation, and multiple transport options including stdio, SSE, and HTTP.
928 114MITUpdated 2026-04-16
78
GreatOverview
Designed to simplify Model Context Protocol server creation, MCP-Framework provides a clean architecture featuring directory-based discovery and robust TypeScript type safety using Zod schemas. The framework includes a command-line interface for scaffolding projects, adding endpoints, and running strict validation to ensure all schema fields are fully documented. It natively supports various transport mechanisms and offers built-in security features such as OAuth 2.1, JWT, and API key authentication for SSE endpoints.
Capabilities
- ▸Directory-based automatic discovery of tools, resources, and prompts
- ▸TypeScript-first development with automatic input type inference from Zod schemas
- ▸Comprehensive build-time and runtime validation enforcing schema field descriptions
- ▸Multi-transport support for stdio, SSE, and HTTP Stream
- ▸Built-in authentication mechanisms including OAuth 2.1, JWT, and API keys for SSE endpoints
- ▸Command-line interface (CLI) for project management and component generation
Best for
Building custom Model Context Protocol servers for AI assistants like Claude Desktop or Cursor, Rapidly scaffolding tools, prompts, and resources using CLI automation, Integrating secure endpoints with built-in authentication for cloud-based MCP architectures
Works with
Claude CodeCursor
Evoa Score breakdown= Σ (score × weight)
78Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%39 → +4.7
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%77 → +6.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total77.8 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The framework supports authentication mechanisms (OAuth 2.1, JWT, API Key) for SSE endpoints. When using experimental HTTP transports with wildcard CORS headers, developers should manually restrict origins to prevent unintended cross-origin exposure.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.