The WebWork MCP Connector lets you manage your WebWork data through AI assistants like Claude and ChatGPT using natural language, without opening the dashboard.
What you can do
Once connected, you can ask your AI assistant to do things like:
- List your projects
- Create and assign tasks
- Start timers
- Add time entries
- Approve timesheets
- Pull reports
- Invite members
The connector is built on the Model Context Protocol (MCP), an open standard supported by a growing range of AI assistants. It works with any MCP-compatible assistant through a single connection, so there’s no separate setup for each tool you use.
Who can use it
The MCP Connector is available to workspace Owners and Executive Managers.
How permissions and security work
Every action runs as you as the signed-in user. The connector respects the same roles and permissions already set up in your workspace and never does anything you aren’t already allowed to do. Connecting an assistant doesn’t expand anyone’s access.
Additional safeguards include:
- OAuth sign-in
Access is granted through OAuth when you sign in, so your login credentials are never shared with the assistant directly. - Confirmation for destructive actions
Actions that delete or archive data require your explicit confirmation before they run. - No separate copy of your data
The connector doesn’t store a separate copy of your WebWork data. - Disconnect anytime
You can disconnect at any time to revoke the assistant’s access.
How to connect
You connect the MCP Connector from within your MCP-compatible assistant and authorize access via OAuth when you sign in. For the full step-by-step setup instructions and the complete list of available actions, see the MCP Connector documentation.
How to disconnect
You can disconnect the MCP Connector at any time to revoke the assistant’s access to your WebWork data. For the exact steps, see the MCP Connector documentation.
Was this article helpful?
Thanks for your feedback.