What
Connect your preferred AI assistant, such as Claude or ChatGPT, to Teamwork.com so you can manage work using natural language.
Why
  • Turn meeting notes, client briefs, support requests, and documentation updates into action.
  • Ask your AI assistant to help with practical work, such as creating projects, updating tasks, reviewing tickets, and drafting content.
  • Reduce manual admin while keeping work connected to your Teamwork.com data and account access.
Who
Teams using Teamwork.com with AI assistants such as Claude or ChatGPT.
When
Use the Teamwork.com MCP server when you want your AI assistant to help manage projects, support work, documentation, workload, budgets, and time tracking in Teamwork.com.

Use AI assistants with Teamwork.com

The Teamwork.com Model Context Protocol (MCP) server powers the connection between AI assistants and Teamwork.com. It helps you turn meeting notes, client briefs, project updates, and documentation needs into action using your Teamwork.com account access.

Use it to support everyday project management workflows, reduce repetitive admin, and get help acting on the information already managed in Teamwork.com.

By connecting your AI assistant to Teamwork.com, teams can spend less time searching for information and updating work manually, and more time acting on project, client, and operational priorities.

What is MCP?

MCP stands for Model Context Protocol. It is a standard that allows AI assistants, such as Claude and ChatGPT, to connect to external tools and services, including Teamwork.com.

The Teamwork.com MCP server acts as the connection between your AI assistant and Teamwork.com. When you ask your AI assistant to complete a supported action, the MCP server uses the relevant Teamwork.com tools to read, create, update, or manage work in your workspace.

On this page

Get help with everyday Teamwork.com workflows

The Teamwork.com MCP server helps your AI assistant support project management AI workflows across Teamwork.com using natural language.

Quickly understand where work needs attention

Review active projects, identify overdue work, check workload capacity, and surface stalled activity before planning meetings or delivery reviews.

Turn conversations into action

Create projects, tasks, milestones, and follow-up work from meeting notes, implementation plans, support conversations, or client briefs.

Prepare for client and leadership updates

Quickly prepare project updates, identify delivery risks, and review workload or budget concerns before client meetings, QBRs, or leadership reviews.

Review support, documentation, and workload

Review customer support activity, search Spaces documentation, track workload capacity, and review project time data across Teamwork.com.

Ask for the outcome you need. The Teamwork.com MCP server helps your AI assistant take supported actions in Teamwork.com using the access available to the connected account.

Connect AI assistants to Teamwork.com

Most MCP-compatible AI assistants follow a similar setup flow: add the Teamwork.com MCP server, enter the dedicated server URL, authenticate with Teamwork.com, and approve access permissions.

  1. Add the Teamwork.com MCP server: Use the connector, integration, app, or MCP setup area in your AI assistant.
  2. Enter the Teamwork.com MCP server URL: https://mcp.ai.teamwork.com.
  3. Authenticate with Teamwork.com: Sign in using the Teamwork.com account you want the AI assistant to use.
  4. Approve access: Review and approve the requested permissions.

Platform-specific setup guides

Claude and ChatGPT both use the same Teamwork.com MCP server URL, though the setup flow differs by platform. Use the guides below for platform-specific setup steps.

Additional MCP-compatible AI assistants and tools, such as Microsoft Copilot, Gemini, Cursor, and other MCP clients, may also support Teamwork.com workflows depending on platform capabilities and MCP support.

Connect Claude to Teamwork.com using the MCP server ↗
Set up Claude with the Teamwork.com MCP server and explore example workflows.
Connect ChatGPT to Teamwork.com using the MCP server ↗
Set up ChatGPT with the Teamwork.com MCP server and explore example workflows.

Available actions depend on the Teamwork.com account used to connect the MCP server. Your AI assistant can only work with information and actions available to that account.

Example AI prompts

Once connected, you can ask Claude or ChatGPT to help with Teamwork.com workflows using prompts like these. Adapt the examples to the projects, clients, teams, and date ranges you want to review.

Example investigative workflow
Identify delays
“Which active projects are behind on milestones this week?”
→
Find blockers
“What tasks are blocking progress on those projects?”
→
Review workload
“Are any blockers assigned to someone over capacity?”

More prompts to try

  • Identify active Teamwork.com projects with overdue tasks, missed milestones, or stalled activity.
  • Look across the next four weeks and tell me who is over capacity and under capacity.
  • Create a project from these client meeting notes and add the key milestones.
  • Summarize project activity for this client so I can prepare a status update.
  • Calculate billable utilization for last month and flag anyone below target.
  • Compare project budget consumed against work completed and flag projects where logged work appears ahead of progress.
  • Show all high-priority tickets waiting for a response and summarize the main customer themes.
  • Create a troubleshooting guide in Teamwork Spaces from these notes and suggest updates for clarity.

Use AI output as a draft or starting point. Review results before sending client updates, making resourcing decisions, or acting on project, budget, or time data.

Supported Teamwork.com areas

The Teamwork.com MCP server supports more than 80 tools across Teamwork.com, Teamwork Desk, and Teamwork Spaces. These tools allow connected AI assistants to read, create, update, and manage supported work in Teamwork.com.

Teamwork.com

  • Projects, project members, categories, and templates.
  • Tasks, task lists, milestones, workflows, activity feeds, and tags.
  • Time logs, timers, workload, teams, users, companies, skills, and job roles.
  • Project and task list budgets where configured.

Teamwork Desk

  • Tickets, replies, internal notes, and file attachments.
  • Customers, companies, inboxes, priorities, statuses, ticket types, and tags.

Teamwork Spaces

  • Spaces, pages, homepages, and page hierarchy.
  • Search, comments, tags, and categories.

Permissions and control

The Teamwork.com MCP server uses the Teamwork.com account connected to the AI assistant. Available information and actions depend on the permissions associated with that account.

Your AI assistant does not get separate access to Teamwork.com. It works through the connected account and follows the permissions available to that account.

Review access carefully before connecting an AI assistant. Any supported action the assistant takes is based on the permissions available to the connected Teamwork.com account.

Frequently asked questions

What is the Teamwork.com MCP server?

The Teamwork.com MCP server connects AI assistants, such as Claude and ChatGPT, to Teamwork.com using the Model Context Protocol (MCP). Once connected, AI assistants can help search, summarize, create, and update supported Teamwork.com work using natural language.

Can I use Claude or ChatGPT with Teamwork.com?

Yes. Claude and ChatGPT are supported through the Teamwork.com MCP server. Use the setup guides linked above for platform-specific setup steps.

Which Teamwork.com products does the MCP server support?

The MCP server supports workflows across Teamwork.com, Teamwork Desk, and Teamwork Spaces.

Can AI assistants create projects and update work in Teamwork.com?

Yes. Supported actions include creating and updating projects, tasks, tickets, documentation, time tracking, and other supported Teamwork.com work.

Does the MCP server use my Teamwork.com permissions?

Yes. Available information and actions depend on the Teamwork.com account used to connect the MCP server.

What should I do if a prompt returns an empty result?

An empty result may mean there is no matching data, or that the relevant information is not currently being tracked in Teamwork.com.