官方说明7 个来源MCP 服务8 天前
bbonnin/openapi-to-mcp
☕ 🏠 🍎 🪟 🐧 - Converts any OpenAPI/Swagger specification into MCP tools automatically
在 GitHub 查看 ↗直链 · 无中转页
配置模板（请按你的客户端调整）
claude mcp add openapi-to-mcp -- npx -y openapi-to-mcp
这是根据仓库名生成的可粘贴骨架，命令行参数与包名请以该项目 README 为准。
- ★ 数取值
- 7 ★ · bbonnin/openapi-to-mcp · 取自 GitHub 搜索 API · （2026-10-16 20:00:20 核对）
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-09 · 最近见到 2026-10-16 · 共见到 32 次 · 被 7 个来源列出
- 评分构成
- 综合分 703 · 7 ★ · 7 个来源 · mcp
常见问题（答案都来自我们的记录）
怎么安装？
我们【没有】从该仓库取到安装命令（我们的 install 覆盖率只有约 4%）。请看它的 README 或 releases 页。
它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
bbonnin/openapi-to-mcp；我们收录于 2026-10-09；最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。第三方质量标记
OpenApi MCP Server
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
> OpenApiMCPServer is an MCP server that automatically converts any OpenAPI/Swagger specification into a set of usable MCP tools.
It analyzes all API endpoints, generates structured tool definitions, and routes tool calls to the underlying REST API.
This allows AI agents to interact with any OpenAPI-based service instantly, without manual tool coding.
Modules
There are several modules:
* openapi-mcp-server: the application that is a MCP server providing the tools defined in an OpenAPI definition (provided as a local file or an HTTP endpoint)
* This server dynamically loads the Swagger content and provides the functions of the API through the MCP protocol, so they can be used in a generative AI architecture without recoding anything
* At startup:
* At runtime:
* openapi-mcp-example: a simple example divided in two parts
* In api package : a fake infrastructure API for managing virtual machines. The API will be invoked by the OpenAPI MCP Server
* In assistant package : an assistant with a simple chat that will use the infrastructure API through the MCP server accessing the API
Run
MCP Server
To start the MCP Server
Example
* Start the example parts, in your IDE, launch:
* The InfrastructureApiServer class
* The InfraAssistantApp class by providing the LLM URL and the MCP server
* The MCP server, in the IDE:
* The OpenApiMcpServer class by providing the OpenAPI location and the Spring profile dev if needed
It analyzes all API endpoints, generates structured tool definitions, and routes tool calls to the underlying REST API.
This allows AI agents to interact with any OpenAPI-based service instantly, without manual tool coding.
Modules
There are several modules:
* openapi-mcp-server: the application that is a MCP server providing the tools defined in an OpenAPI definition (provided as a local file or an HTTP endpoint)
* This server dynamically loads the Swagger content and provides the functions of the API through the MCP protocol, so they can be used in a generative AI architecture without recoding anything
* At startup:
* At runtime:
* openapi-mcp-example: a simple example divided in two parts
* In api package : a fake infrastructure API for managing virtual machines. The API will be invoked by the OpenAPI MCP Server
* In assistant package : an assistant with a simple chat that will use the infrastructure API through the MCP server accessing the API
Run
MCP Server
To start the MCP Server
Example
* Start the example parts, in your IDE, launch:
* The InfrastructureApiServer class
* The InfraAssistantApp class by providing the LLM URL and the MCP server
* The MCP server, in the IDE:
* The OpenApiMcpServer class by providing the OpenAPI location and the Spring profile dev if needed
- 来源
- awesome · https://github.com/bbonnin/openapi-to-mcp
- 按领域浏览
- MCP 服务
- Traction
- 7 ★
- 收录于
- 昨天
更多MCP 服务
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。