What is a Teamwork.com MCP?
It's an MCP server that plugs your agents into Teamwork.com's project management platform via tools. Your agents can invoke these tools to create and update tasks, manage projects and milestones, log time entries, and more.
Teamwork.com offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.
How can I use the Teamwork.com MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- CRM-to-project automation: When a deal is marked closed-won in HubSpot or Salesforce, an agent creates a new Teamwork.com project, assigns the delivery team, and sets up an initial milestone structure without anyone touching Teamwork.com manually
- Time entry logging from Slack: A Slack-based agent listens for time logging commands in a designated channel, parses the task name and duration from the message, and creates a Teamwork.com time entry against the correct project and task
- Overdue task escalation: Each morning, an agent lists tasks that are past their due date across all active projects, groups them by assignee, and posts a personalized overdue summary to each team member in Slack
- End-of-sprint client delivery report: At the close of each sprint, an agent pulls completed tasks and logged time from Teamwork.com, formats a client-facing summary of work delivered, and emails it to the relevant project stakeholders
What are popular tools for Teamwork.com's MCP server?
Here are some of the most commonly used tools:
create_task: adds a new task to a specified task list with fields like name, assignee, due date, and priority. Use this when an agent needs to generate work items automatically based on a trigger in another system
update_task: modifies an existing task's fields, including status, assignee, due date, and description. Good for workflows that reassign tasks, extend deadlines, or move items to in-progress based on external events
list_tasks: returns tasks across a project or task list, filterable by assignee, status, or due date. Useful for agents that need to surface overdue items, build workload summaries, or check completion rates across a portfolio
create_project: creates a new project with name, description, company association, and start and end dates. Call this when an agent needs to spin up a project structure after a business event like a new client contract being signed
create_time_entry: logs a time entry against a specific task or project with duration, date, and description. Helpful when an agent is automating time tracking from an external source like a calendar, a Slack command, or a timer integration
create_milestone: adds a milestone to a project with a deadline and responsible person. Use this when an agent is initializing a project structure and needs to define key delivery checkpoints as part of the setup
What makes Merge Agent Handler's Teamwork.com MCP server better than alternative Teamwork.com MCP servers?
Teamwork.com has its own official MCP server, but there are specific reasons to route it through Merge Agent Handler instead:
- Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Teamwork.com, this means you can prevent task details, client project data, and time entry records containing billing or resource information from being exposed even when the agent has broad access
- Managed authentication and credentials: Merge stores and refreshes Teamwork.com credentials on your behalf. You never embed API keys or OAuth tokens in agent configuration or deal with re-authentication when tokens expire
- Real-time observability and audit trail: Every tool call against Teamwork.com is logged with timestamp, tool name, inputs, and response data. Project managers and security teams can see exactly what an agent created or modified without any additional instrumentation
- Tool Packs and controlled access: Tool Packs let you bundle specific Teamwork.com tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more
How can I start using Merge Agent Handler's Teamwork.com MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account and navigate to Tool Packs (collections of connector tools scoped to a specific use case).
2. Create a new Tool Pack, then find and enable the Teamwork.com connector. Decide which tools fit your workflow: read tools like list_tasks and list_time_entries cover reporting and auditing needs, while write tools like create_task, create_project, and create_time_entry are needed if your agent should take action on project data.
3. Add a Registered User inside the Tool Pack. This is the identity context under which your agent operates. Merge generates a unique MCP URL scoped to this user once it's created.
4. From the Registered User detail page, authenticate Teamwork.com by completing the OAuth flow. Merge stores and manages the credentials going forward.
5. Copy the MCP URL from the Tool Pack detail page and generate an API key from Settings. You'll need both to connect your agent.
6. Add the MCP server to your agent or IDE using the MCP URL and API key. Your Teamwork.com tools are now accessible through that endpoint.