Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@jama-connect what test cases are in the Enphase project?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Unified Jama Connect backend — MCP tools + REST API + built-in viewer.
Features:
Async API client (httpx, OAuth2 client_credentials)
SQLite cache with FTS5 full-text search and TTL invalidation
MCP tools for Windsurf/Claude IDE integration (stdio transport)
REST API (FastAPI on localhost:8765)
Built-in viewer — pre-built static site served at /viewer (no Node.js needed at runtime)
Editor — VS Code extension with rich-text editing, drafts, and push-back
Multi-project support, test management, delta sync, write-back
Cross-platform — Windows + macOS (login service auto-start)
.\scripts\install.ps1./scripts/install.shBoth scripts: check Python ≥3.12, install from internal PyPI (nz-lnx-01), optionally install login service.
pip install jama-mcp-v2 --extra-index-url http://nz-lnx-01/pypi --trusted-host nz-lnx-01Related MCP server: Polarion MCP
# Installed via pip — use the CLI entry point:
jama-rest # REST API + viewer on port 8765
# Development mode via uv:
uv run python -m jama_mcp_v2 --rest-only --port 8765
# MCP mode (for Windsurf — stdin/stdout):
jama-mcp-v2Open http://localhost:8765/viewer in your browser.
Platform | Mechanism | Install | Uninstall |
Windows | Task Scheduler |
|
|
macOS | launchd agent |
|
|
The VS Code extension also offers to install the login service on first activation.
Python ≥3.12
Node.js ≥18 (build-time only, for viewer)
uv (Python package manager)
uv sync # install Python deps
cd jama-viewer && npm ci # install viewer deps./scripts/build-viewer.sh # macOS/Linux
.\scripts\build-viewer.ps1 # WindowsThis runs next build with output: 'export' and copies jama-viewer/out/ → src/jama_mcp_v2/viewer_static/.
# After building viewer:
uv build # creates dist/jama_mcp_v2-0.2.0-py3-none-any.whltwine upload --repository-url http://nz-lnx-01/pypi dist/*{
"jama": {
"command": "uv",
"args": ["run", "--directory", "<path>/jama-mcp-v2", "jama-mcp-v2"],
"env": {
"JAMA_URL": "https://enphase.jamacloud.com",
"JAMA_CLIENT_ID": "...",
"JAMA_CLIENT_SECRET": "...",
"JAMA_CACHE_DIR": "~/.jama-mcp-v2",
"JAMA_REST_PORT": "8765"
}
}
}┌─────────────────────────────────────────────┐
│ jama-mcp-v2 (single process) │
│ │
│ ┌──────────┐ ┌──────────┐ ┌───────────┐ │
│ │ MCP stdio│ │ REST API │ │ Static │ │
│ │ (tools) │ │ /api/* │ │ Viewer │ │
│ │ │ │ /editor/*│ │ /viewer │ │
│ └──────────┘ └──────────┘ └───────────┘ │
│ ↕ │
│ ┌──────────────────────┐ │
│ │ SQLite cache.db │ │
│ │ (FTS5, schema v3) │ │
│ └──────────────────────┘ │
│ ↕ │
│ ┌──────────────────────┐ │
│ │ Jama Cloud API │ │
│ │ (OAuth2 + httpx) │ │
│ └──────────────────────┘ │
└─────────────────────────────────────────────┘This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kailash-enph/jama-connect'
If you have feedback or need assistance with the MCP directory API, please join our Discord server