mcp-octane-server
Enables LLMs to interact with OpenText ALM Octane for querying, creating, and updating defects, stories, tests, and work items through natural language.
README
OpenText ALM Octane MCP Server
A Model Context Protocol (MCP) server for OpenText ALM Octane. This server enables LLMs (like Claude, GitHub Copilot) to seamlessly execute queries, fetch defects, create work items, and interact with the Octane API directly through text instructions.
🚀 Quick Start (NPX)
This package is published on the public NPM registry. The easiest way to run this MCP server is directly via npx (which will download and execute the latest version on the fly), without needing to clone the repository or install anything globally.
Simply provide your ALM Octane credentials as environment variables:
npx -y mcp-octane-server \
OCTANE_URL="https://almoctane-europe.saas.microfocus.com" \
OCTANE_SHARED_SPACE_ID="1001" \
OCTANE_WORKSPACE_ID="1002" \
OCTANE_CLIENT_ID="your-client-id" \
OCTANE_CLIENT_SECRET="your-client-secret"
⚙️ Configuration Variables
The following environment variables are strictly required to start the server:
| Variable | Description |
|---|---|
OCTANE_URL |
Base Server URL of your Octane Instance. (e.g., https://almoctane-europe.saas.microfocus.com) |
OCTANE_SHARED_SPACE_ID |
Numeric or String Identifier for the Shared Space. |
OCTANE_WORKSPACE_ID |
Numeric or String Identifier for the Workspace within the Shared Space. |
OCTANE_CLIENT_ID |
Your API Access Client ID created in Octane settings. |
OCTANE_CLIENT_SECRET |
Your API Access Client Secret corresponding to the Client ID. |
🛠️ IDE & Client Setup
Claude Desktop
Add the following configuration to your mcpServers settings in the Claude configuration file claude_desktop_config.json:
{
"mcpServers": {
"octane": {
"command": "npx",
"args": ["-y", "mcp-octane-server"],
"env": {
"OCTANE_URL": "https://almoctane-europe.saas.microfocus.com",
"OCTANE_SHARED_SPACE_ID": "1001",
"OCTANE_WORKSPACE_ID": "1002",
"OCTANE_CLIENT_ID": "your-client-id",
"OCTANE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Visual Studio Code (MCP Extension)
Create or append to the .vscode/settings.json file in your workspace:
{
"mcp.servers": {
"octane": {
"command": "npx",
"args": ["-y", "mcp-octane-server"],
"env": {
"OCTANE_URL": "https://almoctane-europe.saas.microfocus.com",
"OCTANE_SHARED_SPACE_ID": "1001",
"OCTANE_WORKSPACE_ID": "1002",
"OCTANE_CLIENT_ID": "your-client-id",
"OCTANE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Note: Using npx -y mcp-octane-server in your IDE configuration is recommended as it ensures your client always fetches the latest version of the server from NPM upon startup. If you prefer to install it globally (npm i -g mcp-octane-server), you can replace the command array with simply mcp-octane.
📦 Global Installation
If you intend to run the server frequently from your terminal outside of an IDE, you can install it globally on your system:
npm install -g mcp-octane-server
After global installation, you can run the server using the compiled executable name directly from anywhere:
mcp-octane \
OCTANE_URL="https://almoctane-europe.saas.microfocus.com" \
OCTANE_SHARED_SPACE_ID="1001" \
OCTANE_WORKSPACE_ID="1002" \
OCTANE_CLIENT_ID="your-client-id" \
OCTANE_CLIENT_SECRET="your-client-secret"
�🐳 Docker Usage
You can also run the server via a pre-built Docker image. To run the server ensuring proper network resolution and passing standard input/output:
docker run -i --rm \
-e OCTANE_URL="https://almoctane-europe.saas.microfocus.com" \
-e OCTANE_SHARED_SPACE_ID="1001" \
-e OCTANE_WORKSPACE_ID="1002" \
-e OCTANE_CLIENT_ID="your-client-id" \
-e OCTANE_CLIENT_SECRET="your-client-secret" \
mcp-octane-server
🧠 Available Tools & Prompts
- Tools:
search_all,get_defect_details,create_defect,update_defect,create_story,update_story_status,get_manual_test,get_suite_runs,get_run_history,get_my_work. - Prompts:
triage_assistance(Analyzes defect data using the LLM and suggests 3 root causes from provided context).
🏗️ Local Development
- Clone this repository.
- Run
npm install. - Create a
.envfile referencing.env.example. - Run
npm run buildto compile the app. - Use
npm run startto spin up the local build, or test live usingnpm run dev.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。