Teamwork MCP Server

MCP server to connect to the Teamwork.com API

Local serverstdioTypeScript

What is the Teamwork MCP MCP server?

MCP server to connect to the Teamwork.com API. That is what the teamwork mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

An MCP server that connects to the Teamwork API, providing a simplified interface for interacting with Teamwork projects and tasks.

  • Connect to Teamwork API
  • Retrieve projects and tasks
  • Create, update, and delete tasks
  • RESTful API endpoints
  • Error handling and logging
  • MCP server for integration with Cursor and other applications

The tools it exposes

The server publishes 14 tools. What each one is for:

  • getProjects — Get all projects from Teamwork
  • getCurrentProject — Gets details about the current project
  • createProject — Create a new project in Teamwork
  • getTasks — Get all tasks from Teamwork
  • getTasksByProjectId — Get all tasks from a specific project in Teamwork
  • getTaskListsByProjectId — Get all task lists from a specific project in Teamwork
  • getTasksByTaskListId — Gets all tasks from a specific task list ID from Teamwork
  • getTaskById — Get a specific task by ID from Teamwork
  • createTask — Create a new task in Teamwork
  • createSubTask — Create a new subtask under a parent task in Teamwork
  • updateTask — Update an existing task in Teamwork
  • deleteTask — Delete a task from Teamwork

Getting it running

The server ships on npm as @vizioz/teamwork-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What it needs from you

Configuration is passed through the environment: PROJECT_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Node.js (v14.17 or higher, recommend 18+ or even better latest LTS version) - npm or yarn - Teamwork account with API access

How it compares

Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Teamwork MCP's toolset — getProjects, getCurrentProject, createProject and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Vizioz; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Teamwork MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Teamwork MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
getProjectsGet all projects from Teamwork
getCurrentProjectGets details about the current project
createProjectCreate a new project in Teamwork
getTasksGet all tasks from Teamwork
getTasksByProjectIdGet all tasks from a specific project in Teamwork
getTaskListsByProjectIdGet all task lists from a specific project in Teamwork
getTasksByTaskListIdGets all tasks from a specific task list ID from Teamwork
getTaskByIdGet a specific task by ID from Teamwork
createTaskCreate a new task in Teamwork
createSubTaskCreate a new subtask under a parent task in Teamwork
updateTaskUpdate an existing task in Teamwork
deleteTaskDelete a task from Teamwork
getTasksMetricsCompleteGet the total count of completed tasks in Teamwork
getTasksMetricsLateGet the total count of late tasks in Teamwork

How to install the Teamwork MCP MCP server

{
  "mcpServers": {
    "teamwork": {
      "command": "npx",
      "args": ["-y", "@vizioz/teamwork-mcp"],
      "env": {
        "PROJECT_ID": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js (v14.17 or higher, recommend 18+ or even better latest LTS version) - npm or yarn - Teamwork account with API access
VariableDescriptionRequired
PROJECT_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use Teamwork MCP to getProjects.
  • Use Teamwork MCP to getCurrentProject.
  • Use Teamwork MCP to createProject.

Frequently asked questions

It connects Teamwork MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (getProjects, getCurrentProject, createProject, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Teamwork MCP directly.