Polarion MCP Server
Enables interaction with Siemens Polarion requirements management system through natural language. Supports authentication, project management, work item queries, document access, and requirements analysis.
README
Polarion MCP Server
A Model Context Protocol (MCP) server for interacting with Siemens Polarion requirements management system. No Docker required!
Features
- 🔐 Authentication - Browser-based login with manual token generation
- 📋 Projects - List and get detailed project information
- 📝 Work Items - Query requirements, tasks, and other work items
- 📄 Documents - Access Polarion documents and spaces
- 🔍 Flexible queries - Filter work items with custom queries
- ⚡ Lightweight - Optimized API calls with configurable field sets
- 📦 Easy Installation - One command to get started
Quick Start (30 seconds)
Installation
Option A: Using pip (Recommended)
pip install polarion-mcp
Option B: Using uvx (No local Python needed)
Just use directly in mcp.json (see setup below).
Setup
- Add to your Cursor mcp.json:
{
"mcpServers": {
"polarion": {
"command": "polarion-mcp"
}
}
}
-
Restart Cursor
-
In Cursor chat, authenticate:
Open Polarion login
Set Polarion token: <your-token>
Done! 🎉
Configuration
Connect to Your Polarion Instance
By default connects to http://dev.polarion.atoms.tech/polarion. To use your own instance:
Option 1: Environment Variable
export POLARION_BASE_URL="https://your-polarion.com/polarion"
polarion-mcp
Option 2: In Cursor mcp.json
{
"mcpServers": {
"polarion": {
"command": "polarion-mcp",
"env": {
"POLARION_BASE_URL": "https://your-polarion.com/polarion"
}
}
}
}
Option 3: Using uvx with custom URL
{
"mcpServers": {
"polarion": {
"command": "uvx",
"args": ["polarion-mcp@latest"],
"env": {
"POLARION_BASE_URL": "https://your-polarion.com/polarion"
}
}
}
}
Available Tools
Once authenticated, use these commands in Cursor:
Authentication
Open Polarion login- Opens browser to Polarion loginSet Polarion token: <token>- Saves authentication tokenCheck Polarion status- Verify authentication
Projects
Get Polarion projects- List all projectsGet Polarion project: PROJECT_ID- Get project details
Work Items
Get Polarion work items: PROJECT_ID- List work itemsGet Polarion work items: PROJECT_ID (query: "HMI AND type:requirement")- Filter resultsGet Polarion work item: PROJECT_ID ITEM_ID- Get item details
Documents
Get Polarion document: PROJECT_ID SPACE_ID DOCUMENT_NAME- Access documents
Analysis
polarion_github_requirements_coverage project_id="PROJECT" topic="HMI"- Requirements coverage
Local Development
Prerequisites
- Python 3.10+
- Access to Polarion instance
Installation
git clone https://github.com/Sdunga1/Polarion-MCP.git
cd Polarion-MCP
pip install -e .
Running
polarion-mcp
Troubleshooting
Can't connect?
- Verify
POLARION_BASE_URLis correct - Check if Polarion instance is accessible
- Verify token hasn't expired
Authentication failed?
- Regenerate token in Polarion
- Use:
Open Polarion login→Set Polarion token - Check:
Check Polarion status
Not finding projects?
- Verify user has access to projects in Polarion
- Check authentication:
Check Polarion status
Resources
- GitHub: Polarion-MCP
- PyPI: polarion-mcp
- Issues: Report a bug
License
MIT
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.