Torna MCP Server
Enables interaction with Torna API documentation management platform, allowing users to manage API documents, dictionaries, and modules through natural language commands.
README
Torna MCP Server
一个用于与 Torna 接口文档管理平台交互的 MCP(模型上下文协议)服务器。该服务器基于真实的 Torna OpenAPI 规范,提供了2个核心工具,允许 LLM 通过标准化的接口来管理 Torna 中的 API 文档。
基于真实 Torna API 规范: http://localhost:7700/api
🎉 发布状态
项目已成功发布到PyPI!
- 包名:
torna-mcp - 版本:
1.0.0 - PyPI页面: https://pypi.org/project/torna-mcp/
- 许可证: MIT
- Python支持: >=3.8
🚀 快速开始
安装
方法1:通过PyPI安装(推荐)
# 使用 pip
pip install toma-mcp
# 或使用 uv(推荐)
uv pip install toma-mcp
方法2:从源码安装
git clone https://github.com/li7hai26/torna-mcp.git
cd torna-mcp
pip install -e .
# 或使用 uv
uv pip install -e .
配置环境变量
# 设置Torna服务器地址
export TORNA_URL="http://localhost:7700/api"
# 设置模块访问令牌
export TORNA_TOKEN="your-module-token-here"
获取Token方法:
- 登录 Torna 管理后台
- 选择项目
- 选择模块
- 点击 OpenAPI 标签
- 复制 token
环境变量文件: 如果您使用环境变量文件:
cp .env.example .env
# 编辑 .env 文件,设置您的 TORNA_URL 和 TORNA_TOKEN
启动MCP服务器
torna-mcp
启动后,服务器将在标准输出显示连接信息,您可以将其配置到MCP客户端中使用。
📚 功能特性
核心 API 接口 (2个工具)
基于真实的 Torna OpenAPI 规范实现:
-
推送文档 (
torna_push_document) - 向 Torna 推送 API 文档- 支持创建分类/文件夹
- 支持请求/响应参数定义
- 支持错误码配置
- 支持调试环境设置
-
获取文档 (
torna_get_document) - 获取单个文档详细信息- 获取文档完整信息
- 包括请求/响应参数
- 包括错误码信息
API 规范: 基于 Torna 官方 OpenAPI 实现
🛠️ MCP客户端配置
Cursor
- 打开Cursor设置
- 找到MCP Servers配置
- 添加新服务器:
{
"mcpServers": {
"torna-mcp": {
"command": "torna-mcp",
"env": {
"TORNA_URL": "http://localhost:7700/api",
"TORNA_TOKEN": "your-module-token-here"
}
}
}
}
Claude Desktop
- 编辑Claude配置文件
- 添加MCP服务器配置:
{
"mcpServers": {
"torna-mcp": {
"command": "torna-mcp"
}
}
}
- 重启Claude Desktop
IFlow CLI
# 添加到MCP配置
iflow mcp add toma-mcp
详细的客户端配置说明请参见 MCP_CLIENTS.md
📝 使用示例
推送 API 文档
工具: toma_push_document
参数:
{
"name": "用户登录",
"description": "用户登录接口",
"url": "/api/auth/login",
"http_method": "POST",
"content_type": "application/json",
"request_params": [
{
"name": "username",
"type": "string",
"description": "用户名",
"required": true,
"example": "john_doe"
},
{
"name": "password",
"type": "string",
"description": "密码",
"required": true,
"example": "123456"
}
],
"response_params": [
{
"name": "token",
"type": "string",
"description": "访问令牌"
},
{
"name": "userId",
"type": "string",
"description": "用户ID"
}
],
"author": "张三"
}
获取文档详情
工具: toma_get_document
参数:
{
"doc_id": "doc_123"
}
创建分类(文件夹)
工具: toma_push_document
参数:
{
"name": "用户管理",
"description": "用户相关的API接口",
"url": "",
"http_method": "GET",
"is_folder": true
}
带调试环境的文档
工具: toma_push_document
参数:
{
"name": "商品查询",
"description": "查询商品信息",
"url": "/api/products/{id}",
"http_method": "GET",
"content_type": "application/json",
"path_params": [
{
"name": "id",
"type": "int",
"description": "商品ID",
"required": true,
"example": "123"
}
],
"debug_env_name": "测试环境",
"debug_env_url": "http://localhost:8080"
}
🔧 系统要求
环境要求
- Python: 3.8 或更高版本
- Torna: 私有化部署版本
- MCP客户端: Cursor、Claude Desktop、VS Code等
安装Python环境
- pip (标准Python安装)
- uv (推荐 - 更快更现代的包管理器)
# 安装uv curl -LsSf https://astral.sh/uv/install.sh | sh
📖 详细文档
🐛 问题反馈
如果您在使用过程中遇到问题,请:
- 查看 GitHub Issues
- 在PyPI页面提交反馈
- 发送邮件至: li7hai26@gmail.com
📄 许可证
本项目采用 MIT 许可证,详情请参见 LICENSE 文件。
👨💻 开发者
- 作者: 阿拉丁神灯
- 邮箱: li7hai26@gmail.com
- GitHub: @li7hai26
🔗 相关链接
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.