Connect your AI to Polarion in minutes.
271 REST operations. One server. Every client.
See it in action
Ask questions in plain language. Get real data from your Polarion instance in seconds — no API knowledge required.
What it does
One MCP server that turns the entire Polarion REST API into tool calls your AI assistant can use directly.
Every Polarion REST endpoint exposed as a typed tool — work items, test runs, documents, plans, users, and more. Full coverage, auto-generated from the OpenAPI spec.
auto-generatedClaude Code, Claude Desktop, VS Code GitHub Copilot, ChatGPT Custom GPT, Claude.ai web — one server, five clients, three transports. Pick your stack.
stdio · http · streamableMulti-transport container image with configurable entrypoints. Run locally or deploy on your own infrastructure. No cloud dependency.
self-hostedOptional Polarion SDK docs loaded as tool context. Your AI understands not just the REST API, but the Polarion programming model.
in-context docsPersonal Access Tokens stored in .env, gitignored by default. Separate API keys per transport. TLS support with cert bypass only for internal servers.
pat · env · tlsProject-level configuration is cached on first use. Your AI stays fast even when exploring a complex Polarion instance with dozens of projects.
performanceSetup
Clone the repo, install dependencies, and build. Takes less than two minutes.
npm install && npm run buildAdd your Polarion URL and Personal Access Token. Point your AI client to the server.
API_BASE_URL + BEARER_TOKENOpen your AI assistant and start querying Polarion in plain language. No API knowledge required.
"List open defects in PROJECT"Compatibility
One server, every client. Pick the AI assistant you already use.
Quick Start
Choose your AI client. Copy the config. You're done.
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
// .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_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 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
Polarion & AI Freelancer · Bösger Digital
Nearly a decade of Polarion experience. I built polarion-mcp because I wanted my AI assistants to actually know what's happening in Polarion — not just talk about it.
Open-source, self-hosted, and ready in minutes. No vendor lock-in.