What transport does Mcp Log Proxy support?
It currently only supports the STDIO interface for proxying MCP messages.
@emicklei
基本情報
a web logging proxy for MCP client-server communication
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Mcp Log Proxy is a debugging tool that intercepts and visualizes all messages exchanged between a MCP client and a MCP server through a Web interface. It currently supports only the STDIO transport. It is intended for developers who need to inspect or troubleshoot MCP protocol traffic.
Install via Homebrew (brew tap "emicklei/tap" then brew install emicklei/tap/mcp-log-proxy) or with Go (go install github.com/emicklei/mcp-log-proxy@latest). Run the proxy with the required -command flag, providing the full command line to start the target MCP server (e.g., mcp-log-proxy -command melrose-mcp). Messages are then viewable at http://localhost:5656. Optional flags include -host, -port, -title, and -log.
It currently only supports the STDIO interface for proxying MCP messages.
Install via Homebrew (`brew tap "emicklei/tap"` then `brew install emicklei/tap/mcp-log-proxy`) or with Go (`go install github.com/emicklei/mcp-log-proxy@latest`).
After starting the proxy, open a browser to `http://localhost:5656` (or the configured host and port) to see the web log view.
Yes. Each instance registers itself in `.mcp-log-proxy-instances.json` in your home directory. The web page includes a selector to switch between running proxies, and the proxy automatically chooses an available port if the default is taken.
In the file `.mcp-log-proxy-instances.json` located in your home directory.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント