What is the Model Context Protocol (MCP)?
MCP is a standardized way for tools and LLMs to communicate, allowing tools to expose functionality to any MCP-compatible LLM and enabling LLMs to discover and use tools consistently.
@LostInBrittany
基本情報
A Java program that generates a Quarkus MCP server form an Open API Swagger file
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。
It automatically converts OpenAPI/Swagger specifications into fully functional Model Context Protocol (MCP) servers, allowing LLMs to interact with any REST API through standardized tools. Designed for developers who want to expose REST APIs as MCP-compatible tools.
Use jbang SwaggerToMcpGenerator.java path/to/swagger.json GeneratedMcpServer to generate a server, then jbang GeneratedMcpServer.java to run it. Authentication is configured via environment variables such as API_KEY, BEARER_TOKEN, or API_USERNAME/API_PASSWORD.
MCP is a standardized way for tools and LLMs to communicate, allowing tools to expose functionality to any MCP-compatible LLM and enabling LLMs to discover and use tools consistently.
Use the `--server-index <index>` or `--server-url <url>` option during generation, or set the `SERVER_INDEX` or `SERVER_URL` environment variable at runtime.
Set environment variables: `API_KEY` and `API_KEY_HEADER` for API key auth, `BEARER_TOKEN` for bearer token, or `API_USERNAME` and `API_PASSWORD` for Basic auth.
GET, POST, PUT, DELETE, and PATCH are supported for converting endpoints to MCP tools.
The README lists planned features including form data/multipart support, OAuth 2.0 authentication, a web UI for spec uploads, and WebSocket endpoint support, indicating these are not yet implemented.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
コメント