← Back to work
Open Source · MIT License

polarion-mcp

Connect your AI to Polarion in minutes.

271 REST operations. One server. Every client.

TypeScript Node.js 20+ Polarion REST API
271
REST Operations
5
AI Clients
3
Transports
MIT
License

What it does

271 REST Operations

Every Polarion REST endpoint exposed as a typed tool — work items, test runs, documents, plans, users. Auto-generated from the OpenAPI spec.

Every Major AI Client

Claude Code, Claude Desktop, VS Code GitHub Copilot, ChatGPT Custom GPT and Claude.ai web — one server, five clients, three transports.

Docker-Ready

Multi-transport container image with configurable entrypoints. Run locally or deploy on your own infrastructure. No cloud dependency.

SDK Documentation Access

Optional Polarion SDK docs loaded as tool context — your AI understands not just the REST API but the Polarion programming model.

Secure by Design

Personal Access Tokens stored in .env, gitignored by default. Separate API keys per transport, with TLS support.

Cached Project Config

Project-level configuration is cached on first use. Your AI stays fast even across a complex Polarion instance with dozens of projects.

See it in action

Real screens from the running product, not mockups.

Up and running in 3 steps

01

Clone & Build

Clone the repo, install dependencies and build. Takes less than two minutes.

02

Configure

Add your Polarion URL and Personal Access Token. Point your AI client to the server.

03

Ask

Open your AI assistant and start querying Polarion in plain language. No API knowledge required.

Works with your tools

One server, every client. Pick the AI assistant you already use.

Claude Code
CLI / Agent
stdio
Claude Desktop
macOS / Windows
stdio
GitHub Copilot
VS Code Agent Mode
stdio
ChatGPT
Custom GPT
rest http
Claude.ai
Web App
streamable http

Get building

CLAUDE CODE
claude mcp add polarion-mcp \
  -e API_BASE_URL=https://your-polarion/polarion \
  -e BEARER_TOKEN=your-personal-access-token \
  -- node /path/to/polarion-mcp/build/index.js
VS CODE COPILOT
// .vscode/mcp.json
{
  "servers": {
    "polarion-mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/polarion-mcp/build/index.js"],
      "env": {
        "API_BASE_URL": "https://your-polarion/polarion",
        "BEARER_TOKEN": "your-personal-access-token"
      }
    }
  }
}
CLAUDE DESKTOP
// claude_desktop_config.json
{
  "mcpServers": {
    "polarion-mcp": {
      "command": "node",
      "args": ["/path/to/polarion-mcp/build/index.js"],
      "env": {
        "API_BASE_URL": "https://your-polarion/polarion",
        "BEARER_TOKEN": "your-personal-access-token"
      }
    }
  }
}
DOCKER
docker run -d \
  -e API_BASE_URL=https://your-polarion/polarion \
  -e BEARER_TOKEN=your-personal-access-token \
  -e MCP_HTTP_TOKEN=your-mcp-secret \
  -p 3000:3000 \
  ghcr.io/phillipboesger/polarion-mcp:latest

Ready to connect your AI to Polarion?

Open-source, self-hosted, and ready in minutes. No vendor lock-in.

Or let an AI sum me up — the prompt is already prepared: