mcp-server-polarion
A Model Context Protocol (MCP) server for Polarion ALM. Lets AI assistants read documents, work items, and traceability links — and create, update, and reorganize work items — directly from your Polarion instance.
README
mcp-server-polarion
A Model Context Protocol (MCP) server for Polarion ALM. Lets AI assistants read documents, work items, and traceability links — and create, update, and reorganize work items — directly from your Polarion instance.
Prerequisites
Polarion 2506 or higher is required. Earlier versions lack REST API endpoints this server depends on.
This server is distributed as a Python package and requires uv to run.
Install uv (if not already installed):
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Or via pip:
pip install uv
No other installation is needed — uvx mcp-server-polarion downloads and runs the server automatically.
Setup
Environment Variables
| Variable | Description | Example |
|---|---|---|
POLARION_URL |
Base URL of your Polarion instance | https://polarion.example.com |
POLARION_TOKEN |
Personal Access Token for authentication | your-personal-access-token |
POLARION_VERIFY_SSL |
Verify TLS certificates (default true). Set false for self-signed certs on trusted networks. |
true |
MCP client
envobjects must use string values, so booleans are quoted (e.g."POLARION_VERIFY_SSL": "true"). The server parses"true"/"false"into a realbool.
<details> <summary><b>VS Code (GitHub Copilot)</b></summary>
Add to .vscode/mcp.json:
{
"servers": {
"mcp-server-polarion": {
"type": "stdio",
"command": "uvx",
"args": ["mcp-server-polarion"],
"env": {
"POLARION_URL": "https://polarion.example.com",
"POLARION_TOKEN": "your-personal-access-token",
"POLARION_VERIFY_SSL": "true"
}
}
}
}
</details>
<details> <summary><b>Claude Desktop</b></summary>
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-server-polarion": {
"command": "uvx",
"args": ["mcp-server-polarion"],
"env": {
"POLARION_URL": "https://polarion.example.com",
"POLARION_TOKEN": "your-personal-access-token",
"POLARION_VERIFY_SSL": "true"
}
}
}
}
</details>
<details> <summary><b>Cursor</b></summary>
Add to Cursor MCP settings:
{
"mcpServers": {
"mcp-server-polarion": {
"command": "uvx",
"args": ["mcp-server-polarion"],
"env": {
"POLARION_URL": "https://polarion.example.com",
"POLARION_TOKEN": "your-personal-access-token",
"POLARION_VERIFY_SSL": "true"
}
}
}
}
</details>
<details> <summary><b>Claude Code</b></summary>
Register via the claude mcp add command:
claude mcp add mcp-server-polarion \
-e POLARION_URL=https://polarion.example.com \
-e POLARION_TOKEN=your-personal-access-token \
-e POLARION_VERIFY_SSL=true \
-- uvx mcp-server-polarion
</details>
Tools
Read
| Tool | Description |
|---|---|
list_projects |
List accessible projects |
list_documents |
List documents in a project |
list_work_items |
Search work items with Lucene or SQL queries |
get_document |
Get document metadata, optionally with the raw body HTML |
read_document |
Render a document end-to-end as Markdown |
read_document_parts |
List a document's structural parts with embedded work item metadata |
get_work_item |
Get work item details with the body as raw HTML |
read_work_item |
Get work item details with the body as Markdown |
list_work_item_links |
List a work item's outgoing or incoming links |
list_document_comments |
List a document's comments with thread relationships |
list_document_enum_options |
Resolve valid enum ids for a document field |
list_work_item_enum_options |
Resolve valid enum ids for a work item field |
All list tools support pagination via page_size (1–100) and page_number parameters.
Write
| Tool | Description |
|---|---|
create_work_item |
Create a new work item |
update_work_item |
Update an existing work item |
create_document |
Create a new document |
update_document |
Update document metadata, body, or workflow status |
create_work_item_links |
Create one or more outgoing links from a source work item |
update_work_item_links |
Update suspect / revision on one or more outgoing links |
delete_work_item_links |
Delete one or more outgoing links from a source work item |
move_work_item_to_document |
Attach a work item to a document at a chosen position |
move_work_item_from_document |
Detach a work item from its document |
create_document_comments |
Add one or more comments or replies to a document |
update_document_comment |
Resolve or re-open a document comment |
Example Prompts
"List the documents in space 'Specifications' of project MCPT."
"Read the SRS document of project MCPT and summarize each open requirement."
"Find every approved requirement in project MCPT whose title starts with 'Auth' and show me their owning document."
"Show the outgoing and incoming links for MCPT-042 and flag any child task that is still open."
"Which requirements in the SRS document have no 'verifies' back link from a test case?"
"List the valid status values for a defect in project MCPT, then move MCPT-077 to 'in_review'."
"Create a task in project MCPT titled 'Refactor authentication module' and link it to MCPT-042 as 'relates_to'."
"Add a new requirement under section 3.2 of the SRS document with the body I just drafted."
"Move MCPT-201 into the SRS document right after MCPT-150."
"Detach MCPT-077 from its document so I can rework it as a standalone task."
"Bump MCPT-042's priority to 90, set severity to 'major', and approve the workflow."
License
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。
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。
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。
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。