jama-connect
Click on "Deploy 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-connectwhat 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.
jama-connect
Unified Jama Connect package — MCP server + REST API + web viewer + VS Code extension.
Version: 0.5.0 | Repo: github.com/kailash-enph/jama-connect
Features
MCP Server — Jama integration for Windsurf/Devin (stdio transport)
REST API — FastAPI on localhost:8765 with full Jama CRUD
Web Viewer — pre-built static site at
/viewer(no Node.js at runtime)VS Code Extension — rich-text editor for Jama items with TipTap
Daemon Mode —
jama-connect --daemonruns MCP + REST in one processCache Seed — pre-populated Enphase Jama cache (91 projects, 8500+ items) downloaded from SharePoint on first run
Devin Symlink —
jama-post-installcreates junction at~/.devin/mcp-servers/jama-connectSQLite Cache — FTS5 full-text search, schema v3, TTL invalidation
Cross-platform — Windows, macOS, Linux (pure Python, no WSL needed)
Related MCP server: mcp-xray-cloud
Installation
pip install jama-connectOr from wheel:
pip install dist/jama_connect-0.5.0-py3-none-any.whlPost-Install
jama-post-install # Creates symlink in ~/.devin/mcp-servers/CLI Commands
Command | What it does |
| MCP server (stdio) for Windsurf/Devin |
| MCP + REST API in one process (recommended) |
| REST API + web viewer standalone |
| Install VS Code extension |
| Create symlink in |
Running
Daemon Mode (recommended for Devin/Windsurf)
Starts both MCP (stdio) and REST API (port 8765) in one process:
jama-connect --daemonThis is what mcp_config.json uses — no separate jama-rest terminal needed.
REST API Only
jama-restOpen http://localhost:8765/viewer in your browser.
VS Code Extension
jama-editor # Installs bundled VSIX to VS CodeThen open VS Code → Jama Editor sidebar. Requires jama-rest or jama-connect --daemon running.
First-Run Cache Seed
On first run (no ~/.jama-mcp-v2/projects/<id>.db exists), jama-connect will:
Check
~/Downloads/,~/.jama-mcp-v2/, cwd, and system temp forcache_seed.db.gzIf not found, open the SharePoint link in your browser and wait for you to download
After download, auto-find and decompress (44 MB → 321 MB)
This gives you instant access to 91 projects and 8500+ items without a full sync.
MCP Config (for Windsurf/Devin)
{
"jama-mcp-v2": {
"command": "jama-connect",
"args": [],
"env": {
"JAMA_URL": "https://enphase.jamacloud.com",
"JAMA_CLIENT_ID": "your-client-id",
"JAMA_CLIENT_SECRET": "your-client-secret",
"JAMA_CACHE_DIR": "~/.jama-mcp-v2",
"JAMA_REST_PORT": "8765"
}
}
}Credential Auto-Loading
All commands (jama-connect, jama-rest, jama-editor) automatically find credentials from your IDE's MCP config — no need to set env vars manually.
Searched in order (first match wins):
IDE | Config path |
Windsurf |
|
Devin |
|
Claude Desktop |
|
Cursor |
|
Looks for a jama-mcp-v2, jama-connect, or jama entry and reads the env block.
If no config is found, set env vars directly:
set JAMA_CLIENT_ID=your-client-id
set JAMA_CLIENT_SECRET=your-client-secretEnvironment Variables
Variable | Default | Purpose |
|
| Jama instance URL |
| auto from mcp_config | OAuth2 client ID |
| auto from mcp_config | OAuth2 client secret |
|
| Cache directory |
|
| REST API port |
|
| Jama API concurrency limit |
| (unset) | LAN cache server URL (e.g. |
Development
Prerequisites
Python ≥3.12
Node.js ≥18 (build-time only, for viewer)
uv (Python package manager)
Dev Setup
uv sync # install Python deps
cd viewer && npm ci # install viewer depsBuild
.\build-package.ps1 # Windows (viewer + extension + wheel)
./build-package.sh # macOS/Linux
uv build # wheel onlyTest
uv run pytest tests/ -v # Python tests
cd vscode-extension && npm test # TypeScript testsPublish
twine upload --repository-url http://nz-lnx-01/pypi dist/*Architecture
┌──────────────────────────────────────────────────┐
│ jama-connect (single process) │
│ │
│ ┌──────────┐ ┌──────────┐ ┌───────────┐ │
│ │ MCP stdio│ │ REST API │ │ Static │ │
│ │ (tools) │ │ /api/* │ │ Viewer │ │
│ │ │ │ /editor/*│ │ /viewer │ │
│ └──────────┘ └──────────┘ └───────────┘ │
│ ↕ │
│ ┌──────────────────────┐ │
│ │ SQLite cache.db │ │
│ │ (FTS5, schema v3) │ │
│ │ + editor_db.sqlite │ │
│ └──────────────────────┘ │
│ ↕ │
│ ┌──────────────────────┐ │
│ │ Jama Cloud API │ │
│ │ (OAuth2 + httpx) │ │
│ └──────────────────────┘ │
└──────────────────────────────────────────────────┘
Daemon mode: MCP stdio (main thread) + REST API (background thread)
→ one process, shared cache, shared API clientFiles
Location | Purpose |
| Jama item/test cache |
| Editor drafts/schema |
| Service logs |
| Devin symlink/junction |
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for AI access to Swagger by SmartBear.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseCqualityCmaintenanceAn MCP server that enables AI assistants to interact with JIRA, allowing for querying issue details, creating and updating work items, and managing attachments through a standardized interface.124MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that connects AI assistants to Xray Cloud for Jira test management, enabling natural language interaction with tests, test plans, executions, and CI result imports.MIT
- FlicenseNot gradedqualityAmaintenanceAn MCP server that gives an AI agent read and write access to a live SysML v2 model through the vendor-neutral OMG SysML v2 REST API.2-
- AlicenseNot gradedqualityBmaintenanceMCP server for Atlassian Confluence and Jira, enabling AI assistants to search, create, and update issues and pages via natural language.MIT