Developer tools
Teamwork.com for AI agents.
Managed auth, ready-made tools.
List projects and tasks, create, update and complete tasks, comment and log time in Teamwork.com on behalf of each of your users.
About Teamwork.com
With the Teamwork.com connector, your agent works in each user’s own Teamwork.com site. It can list projects and tasks, create or update a task, mark it complete, add a comment and log time, using only the tools your project allows.
Teamwork.com is a project management platform for client work and agencies.
Tools
What your agent can do in Teamwork.com.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Teamwork.com connection.
-
List projects
Readteamwork_list_projectsList the projects the user can see.
-
List tasks
Readteamwork_list_tasksList tasks in a project or assigned to the user.
-
Create a task
Writeteamwork_create_taskCreate a task in a task list.
-
Update a task
Writeteamwork_update_taskChange a task's details, assignee or due date.
-
Complete a task
Writeteamwork_complete_taskMark a task as complete.
-
Add a comment
Writeteamwork_add_commentComment on a task.
-
Log time
Writeteamwork_log_timeLog time against a task or project.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Teamwork.com, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read and create tasks, and switch off
teamwork_log_timeso it can never add time entries. -
Restrict what the agent reaches
Choose the endpoints a project may use, for example tasks but not time tracking. A call outside them is refused.
Get started
Connect Teamwork.com
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Teamwork.com
Each end user authorizes their own Teamwork.com account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Teamwork.com account, once. const connection = await agent200 .user("user_123") .connect("teamwork"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Teamwork.com tools
Name the user, the model and the tools. The model decides which Teamwork.com tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "What tasks are due this week on the website redesign project", tools: ["teamwork"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, on Teamwork.com's own sign-in page. You never see or store their Teamwork.com password.
-
What access is requested
The access the connection needs to their projects, tasks and time, listed on the authorization screen. Users can remove the app later from their Teamwork.com account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Teamwork.com connector and how to use it.
Connector: Teamwork.com, through Agent200. In code: "teamwork". What it does: List projects and tasks, create, update and complete tasks, comment and log time in Teamwork.com on behalf of each of your users. Page: https://www.agent200.com/connectors/teamwork/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Teamwork.com's own page, through the authorization link Agent200 returns. Never ask a user for a Teamwork.com password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: teamwork_list_projects, teamwork_list_tasks. Write tools: teamwork_create_task, teamwork_update_task, teamwork_complete_task, teamwork_add_comment, teamwork_log_time. Name "teamwork" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/teamwork/framework/claude/ https://www.agent200.com/connectors/teamwork/framework/chatgpt/ https://www.agent200.com/connectors/teamwork/framework/claude-code/ https://www.agent200.com/connectors/teamwork/framework/muse/ https://www.agent200.com/connectors/teamwork/framework/grok-bot/ https://www.agent200.com/connectors/teamwork/framework/openai-dots/ https://www.agent200.com/connectors/teamwork/framework/claude-duet/ https://www.agent200.com/connectors/teamwork/framework/hermes-agent/ https://www.agent200.com/connectors/teamwork/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/teamwork.md
Guides
Use Teamwork.com with the AI you build on.
Step-by-step setup for Teamwork.com with a specific model, assistant or agent framework.
-
Teamwork.com + Claude
How to connect Teamwork.com to Claude
-
Teamwork.com + ChatGPT
How to connect Teamwork.com to ChatGPT
-
Teamwork.com + Claude Code
How to connect Teamwork.com to Claude Code
-
Teamwork.com + Muse
How to connect Teamwork.com to Muse
-
Teamwork.com + Grok Bot
How to connect Teamwork.com to Grok Bot
-
Teamwork.com + OpenAI Dots
How to connect Teamwork.com to OpenAI Dots
-
Teamwork.com + Claude Duet
How to connect Teamwork.com to Claude Duet
-
Teamwork.com + Hermes Agent
How to connect Teamwork.com to Hermes Agent
-
Teamwork.com + OpenClaw
How to connect Teamwork.com to OpenClaw
FAQ
Teamwork.com and Agent200, answered.
Who handles the Teamwork.com OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Teamwork.com.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Teamwork.com connection, never another user's. It cannot reach anything the user or Teamwork.com has not authorized.
Can I limit what my agent can do in Teamwork.com?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.