OpenAPI to MCP Server

A server that converts OpenAPI specifications into the Model Context Protocol (MCP).

- 将OpenAPI规范转换为MCP服务
- 支持http header透传
- 支持本地mcp 通用stdio使用方式、也支持docker部署为mcp server后通过streamable http方式使用

本项目支持通过多种客户端配置 MCP 服务器，以便与各种 IDE 或工具集成。以下是一些常见客户端的配置示例：

对于基于 Windsurf 框架的客户端（如 Cursor 和 Claude），您可以在~/.codeium/windsurf/mcp_config.json文件中配置 MCP 服务器。以下是一个示例配置：

{ "mcpServers": { "openapi2mcpserver": { "disabled": false, "command": "uvx", "args": [ "openapi2mcpserver" ], "env": { "BASE_URL": "your_openapi3.0_host", "OPEN_API_DOC_JSON_URL": "your_openapi3.0_host doc json url" } } } }

请将BASE_URL,OPEN_API_DOC_JSON_URL替换为您的实际 OpenAPI 服务器地址和文档 JSON URL。

对于 Cline 客户端，您可以在其配置文件中添加类似的 MCP 服务器配置。具体的配置方式请参考 Cline 的官方文档。通常，您需要指定服务器的名称、命令、参数和环境变量。

// Cline 配置文件示例 (具体格式请参考 Cline 文档) { "mcpServers": { "openapi2mcpserver": { "command": "uvx", "args": [ "openapi2mcpserver" ], "env": { "BASE_URL": "your_openapi3.0_host", "OPEN_API_DOC_JSON_URL": "your_openapi3.0_host doc json url" } } } }

请将示例中的占位符替换为您的实际 OpenAPI 服务器地址和文档 JSON URL，并根据 Cline 的具体配置格式进行调整。
- 克隆仓库
- 安装依赖：pip install -r requirements.txt
- 配置环境变量（参见下文）

BASE_URL=https://api.xxx.com OPEN_API_DOC_JSON_URL=https://api.xxx.com/api/v3/api-docs/default

docker run -d -p 9087:9087 -e BASE_URL=http://xxx.xx.xx.xxx:8044/xiaogj-ai-api -e OPEN_API_DOC_JSON_URL=http://xxx.xx.xx.xxx:8044/xiaogj-ai-api/v3/api-docs -e SERVER_NAME=OpenAPI2MCP-Docker-Server -e "ROUTE_MAPS=[{\"methods\":[\"GET\",\"POST\"],\"pattern\":\"^/tool/.*\"}]" jeweis/openapi2mcp:latest

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Converts OpenAPI/Swagger specifications to Model Context Protocol (MCP) format, providing a modern Web UI and a backend service.

Explore and analyze OpenAPI specifications from local files or remote URLs.

Serves multiple OpenAPI specifications to enable LLM-powered IDE integrations.

A server for splitting and extracting parts of OpenAPI specifications using Redocly CLI.

MCP server for API documentation, supporting GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

A server that dynamically creates MCP endpoints from any OpenAPI specification URL.

A TypeScript MCP server to access Apifox API data via Stdio.

Provides API documentation from Apifox projects as a data source for AI programming tools that support MCP.