Teamwork.com MCP Server
Connect Teamwork.com to your AI agents with the Teamwork.com MCP server.
Updated
What is Teamwork.com MCP?
The Teamwork.com MCP server is a Model Context Protocol server that connects Teamwork.com to AI agents and assistants as a set of tools. With it connected, an agent can work with Teamwork.com (client work management — projects, tasks, time tracking, milestones, workloads) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses no authentication, so you point your client at the server URL, authorize once, and the Teamwork.com tools become available to the model.
Connect the Teamwork.com MCP server
Connect Teamwork.com MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the Teamwork.com MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (no authentication) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a Teamwork.com tool to confirm the connection is live.
Connect Teamwork.com MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add Teamwork.com
Provide the Teamwork.com MCP server URL or command and complete authentication.
- 3
Test
Reference Teamwork.com from chat to confirm Cursor can reach the tools.
Sample use cases
Auto-log time entries from calendar events or meeting notes
The agent matches calendar blocks to Teamwork tasks and creates time entries without manual tracking.
Generate client-facing project status reports
The agent pulls task progress, milestone status, and time logged, then formats a polished update for the client.
Create tasks from Slack or email requests
The agent parses the request, creates a Teamwork task with the right project and assignee, and confirms back.
Track project budgets and alert when approaching limits
A scheduled agent checks billable hours against budget caps and warns the project lead before overruns.
Assign tasks based on team workload and availability
The agent reviews open task counts and recent time entries to suggest or make assignments that balance the load.
Surface overdue milestones and escalate to project leads
The agent checks milestone due dates daily and notifies the responsible lead when a milestone is at risk.
Compile weekly billable hours summaries across projects
The agent aggregates time entries by project and person, highlighting utilization rates and unbilled time.
Using Teamwork.com MCP with Gamut
On Gamut, the Teamwork.com MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through Teamwork.com and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is the Teamwork.com MCP server?
It is a Model Context Protocol server that exposes Teamwork.com to AI agents as tools so they can manage client work — projects, tasks, time tracking, milestones, and workloads.
How do I connect the Teamwork.com MCP server?
Point your MCP client (Claude, Cursor, or Gamut) at the Teamwork.com MCP server URL and complete authentication. See the official documentation for the exact URL and scopes.
Can I use Teamwork.com MCP with Gamut?
Yes — Gamut supports the Teamwork.com MCP server, so your agents can use it as a tool in automated, triggered workflows.
Can the agent track time and log billable hours?
Yes. If the API token has write access to time entries, the agent can create, update, and delete time logs. This pairs well with scheduled agents that auto-log time from calendar events.
Does Teamwork MCP work with multiple client projects?
Yes. The server connects to your Teamwork account, which can contain many projects. The agent can list, filter, and switch between them as needed.
Which authentication method does the Teamwork MCP server use?
The server authenticates using a bearer token or API key from your Teamwork account. No OAuth flow is required — generate a token in Teamwork's settings and pass it to the MCP server configuration.
Can the agent access Teamwork's reporting and budget features?
The agent can read task data, time entries, and milestones to build reports. Budget tracking works by comparing logged time against project estimates, which the agent calculates from the available data.