Metadata-Version: 2.4
Name: rocketlane-mcp
Version: 0.2.0
Summary: MCP server exposing Rocketlane CSM data — projects, tasks, team workload, and weekly reviews
Project-URL: Homepage, https://github.com/minhlecsm/rocketlane-mcp
Project-URL: Issues, https://github.com/minhlecsm/rocketlane-mcp/issues
License: MIT
Keywords: csm,customer-success,mcp,rocketlane
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.11
Requires-Dist: fastmcp>=2.0
Requires-Dist: python-dotenv>=1.0
Requires-Dist: requests>=2.31
Provides-Extra: dev
Requires-Dist: pytest-mock>=3.12; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: responses>=0.25; extra == 'dev'
Description-Content-Type: text/markdown

# rocketlane-mcp

An MCP server that exposes your [Rocketlane](https://www.rocketlane.com) CSM data to Claude and other MCP-compatible AI clients. Ask questions about project health, team workload, tasks, and generate weekly reviews — without leaving your AI assistant.

## Tools

| Tool | Description |
|---|---|
| `get_projects_snapshot` | All active projects with status, CSM owner, and progress % |
| `get_csm_workload` | Per-CSM active project count and overdue task count |
| `get_project_updates` | Recent project updates (scope by project or all, configurable lookback window) |
| `get_all_tasks` | All tasks across active projects — filter by project or assignee name |
| `get_team_members` | All active team members with user ID and email |
| `parse_tasks_from_notes` | Parse meeting notes into structured task drafts for review |
| `create_tasks` | Create confirmed tasks in Rocketlane (call after `parse_tasks_from_notes`) |
| `create_project` | Create a new Rocketlane project |
| `push_weekly_review_to_lark` | Generate a weekly CS review doc and push it to Lark Docs *(optional — requires Lark credentials)* |

## Quickstart

### Claude Desktop (recommended)

Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):

```json
{
  "mcpServers": {
    "rocketlane-csm": {
      "command": "uvx",
      "args": ["rocketlane-mcp"],
      "env": {
        "ROCKETLANE_API_KEY": "your_rocketlane_api_key_here",
        "ROCKETLANE_BASE_URL": "https://api.rocketlane.com/api/1.0"
      }
    }
  }
}
```

Restart Claude Desktop. No separate install step needed — `uvx` fetches and runs the package automatically.

### Install via pip

```bash
pip install rocketlane-mcp
```

Then run:

```bash
ROCKETLANE_API_KEY=your_key rocketlane-mcp
```

Or create a `.env` file (see [`.env.example`](.env.example)) and run `rocketlane-mcp` directly.

## Configuration

| Variable | Required | Description |
|---|---|---|
| `ROCKETLANE_API_KEY` | Yes | Your Rocketlane API key (Settings → Integrations → API) |
| `ROCKETLANE_BASE_URL` | Yes | `https://api.rocketlane.com/api/1.0` |
| `LARK_APP_ID` | No | Lark app ID — only needed for `push_weekly_review_to_lark` |
| `LARK_APP_SECRET` | No | Lark app secret |
| `LARK_FOLDER_TOKEN` | No | Lark folder token where review docs will be created |

## Example prompts

- *"Show me all active projects and their health status."*
- *"Which CSM has the most overdue tasks this week?"*
- *"What updates have been posted in the last 3 days?"*
- *"Parse these meeting notes and create tasks for the team: ..."*
- *"Push this week's CS review to Lark."*

## Development

```bash
git clone https://github.com/minhlecsm/rocketlane-mcp
cd rocketlane-mcp
pip install -e '.[dev]'
cp .env.example .env  # fill in your credentials
pytest
```

## License

MIT
