#
ENJA

mcp-proxy

nuwax-ai/mcp-proxy

A comprehensive Rust-based Model Context Protocol (MCP) proxy workspace that handles protocol conversion between SSE, HTTP, and stdio, alongside supplementary multi-format document parsing and voice transcription services.

7 14No licenseUpdated 2026-08-13

Overview

The mcp-proxy workspace provides a robust suite of tools implemented in Rust and Python to bridge various MCP communication channels. It features specialized proxies for Server-Sent Events (SSE) and streamable HTTP, a main stdio conversion tool, high-performance document parsing capabilities for formats like PDF and Office documents, and a speech-to-text service powered by Whisper.

Capabilities

  • SSE and Streamable HTTP to stdio protocol conversion
  • Multi-format document parsing via MinerU and MarkItDown
  • Speech-to-text transcription with Whisper models
  • Protocol auto-detection and health check monitoring
  • Text embedding and Alibaba Cloud OSS integration

Best for

Converting remote MCP services (SSE/HTTP) to local stdio protocol for AI agents, Parsing multi-format documents (PDF, Word, Excel, PowerPoint) for LLM context ingestion, Running local speech-to-text transcription with Whisper model integration

Works with

Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
66
Task usefulness20%88 → +17.6

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%85 → +12.8

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

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%43 → +5.2

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%80 → +8.0

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%39 → +3.1

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%75 → +3.8

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 total77.4 / 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

Downloads and executes installation scripts via curl/irm; ensure binaries are fetched from trusted sources.

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.