soap-api-gateway

soap-api-gateway

Converts SOAP WSDL services into a REST interface and provides MCP tools to describe, invoke, and manage SOAP operations with caching and WS-Security support.

Category
访问服务器

README

🛰 Hybrid SOAP→REST Gateway (Async + Cache + MCP + FastAPI)

A production‑grade gateway that:

  • Converts SOAP WSDL services into a REST‑style interface.
  • Runs FastAPI HTTP API and MCP server as separate processes in the different containers.
  • Supports WS‑Security UsernameToken authentication from .env.
  • Caches raw WSDL XML and fully processed WSDL (Zeep client, docs, examples).
  • Allows manual cache clear and manual processed WSDL refresh via HTTP or MCP.
  • Uses .env for environment‑specific configuration.

📂 Project Structure

.
├── soap_gateway.py      # Shared SOAP→REST logic
├── fastapi_app.py       # FastAPI HTTP API
├── mcp_server.py        # MCP server
├── requirements.txt     # Python dependencies
├── Dockerfile           # Container build instructions
├── docker-compose.yml   # docker compose file
├── .env                 # Environment variables
└── README.md            # This file

🚀 Features

  • Dual‑process: FastAPI and MCP run independently — no blocking.
  • Async‑ready: Core functions can be adapted for async.
  • Caching:
    • Raw WSDL XML
    • Fully processed WSDL (Zeep client, operation docs, element docs)
  • Clear cache: /clear_cache endpoint or MCP clear() tool.
  • Refresh processed WSDL: /refresh_wsdl endpoint or MCP refresh_wsdl() tool.
  • Dockerized: Minimal image with supervisord managing both processes.
  • Configurable health check: WSDL URL set via HEALTHCHECK_WSDL_URL env var.

⚙️ Environment Variables

Variable Purpose Default
HEALTHCHECK_WSDL_URL WSDL URL used by health check and as default for /describe and MCP describe http://example.com?wsdl
SOAP_USERNAME Username for WS‑Security UsernameToken authentication (none)
SOAP_PASSWORD Password for WS‑Security UsernameToken authentication (none)
DEBUG If true, returns full error + traceback in responses false
PORT Port for FastAPI HTTP server 9000

📄 Example .env

HEALTHCHECK_WSDL_URL=https://dev.example.com/service?wsdl
SOAP_USERNAME=myuser
SOAP_PASSWORD=supersecret
DEBUG=true
PORT=9000

🐳 Docker Deployment

docker compose up -d

🛠 Usage

1. HTTP API (FastAPI)

  • http://localhost:9000/docs - FastAPI documentation
  • POST /describe — List operations and input schema.
  • POST /invoke — Call a SOAP operation.
  • POST /clear_cache — Flush all caches.
  • POST /refresh_wsdl — Force rebuild of processed WSDL cache.

2. MCP Server

Tools:

  • describe(wsdl_url=None, operation=None, username=None, password=None)
  • invoke(wsdl_url=None, endpoint_url, operation, params, username=None, password=None)
  • clear()
  • refresh_wsdl(wsdl_url=None, username=None, password=None, version="v1")

HTTP MCP transport (mounted at /mcp)

The MCP wrapper in mcp_server.py mounts an HTTP transport at /mcp by default. When calling the HTTP MCP endpoint, send a JSON POST where tool is the tool name and args is an object containing the tool arguments. Example payload:

{
  "tool": "describe",
  "args": {
    "wsdl_url": "https://example.com/service?wsdl",
    "operation": null,
    "username": null,
    "password": null
  }
}

The endpoint will return a JSON response containing the tool result (same shape as the internal function return values). This is useful for MCP agents that communicate over HTTP instead of stdio.


🤝 MCP Agent Configuration

Local spawn (stdio)

{
  "mcpServers": {
    "soap-gateway": {
      "type": "stdio",
      "command": "python",
      "args": ["mcp_server.py"],
      "env": {
        "HEALTHCHECK_WSDL_URL": "https://dev.example.com/service?wsdl",
        "SOAP_USERNAME": "myuser",
        "SOAP_PASSWORD": "supersecret"
      }
    }
  }
}

Remote/HTTP

{
  "mcpServers": {
    "soap-gateway": {
      "type": "http",
      "url": "http://your-server-host:9010/mcp",
      "env": {
        "HEALTHCHECK_WSDL_URL": "https://prod.example.com/service?wsdl",
        "SOAP_USERNAME": "myuser",
        "SOAP_PASSWORD": "supersecret"
      }
    }
  }
}

🐳 MCP Configuration for Docker Deployment

When running inside Docker, connect over HTTP:

{
  "mcpServers": {
    "soap-gateway": {
      "type": "http",
      "url": "http://localhost:9010/mcp",
      "env": {
        "HEALTHCHECK_WSDL_URL": "https://dev.example.com/service?wsdl",
        "SOAP_USERNAME": "myuser",
        "SOAP_PASSWORD": "supersecret"
      }
    }
  }
}

❤️ Health Check

ENV HEALTHCHECK_WSDL_URL="http://example.com?wsdl"
HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
  CMD curl -sf http://localhost:9000/describe \
       -H "Content-Type: application/json" \
       -d "{\"wsdl_url\":\"${HEALTHCHECK_WSDL_URL}\"}" || exit 1

🧹 Cache Management

  • Automatic: Processed WSDL cache is built on first use and reused until cleared or refreshed.
  • Manual clear:
    • HTTP: POST /clear_cache
    • MCP: clear() tool
  • Manual refresh:
    • HTTP: POST /refresh_wsdl
    • MCP: refresh_wsdl() tool

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选