# Wrike for AI agents. Managed auth, ready-made tools.

> List, create and update tasks, browse folders and add comments in Wrike on behalf of each of your users.

- Page: https://www.agent200.com/connectors/wrike/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `wrike`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Wrike, through Agent200. In code: "wrike".
What it does: List, create and update tasks, browse folders and add comments in Wrike on behalf of each of your users.
Page: https://www.agent200.com/connectors/wrike/

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 Wrike's own page, through the authorization link Agent200 returns. Never ask a user for a Wrike 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: wrike_list_tasks, wrike_get_task, wrike_list_folders, wrike_list_comments. Write tools: wrike_create_task, wrike_update_task, wrike_add_comment. Name "wrike" 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/wrike/framework/claude/
   https://www.agent200.com/connectors/wrike/framework/chatgpt/
   https://www.agent200.com/connectors/wrike/framework/claude-code/
   https://www.agent200.com/connectors/wrike/framework/muse/
   https://www.agent200.com/connectors/wrike/framework/grok-bot/
   https://www.agent200.com/connectors/wrike/framework/openai-dots/
   https://www.agent200.com/connectors/wrike/framework/claude-duet/
   https://www.agent200.com/connectors/wrike/framework/hermes-agent/
   https://www.agent200.com/connectors/wrike/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Wrike connector, your agent works in each user's own Wrike workspace. It can list and read tasks, create or update a task, browse folders and projects, and read or add comments, using only the tools your project allows.

Wrike is a work management platform for planning projects and tracking tasks across teams.

## Wrike tools

- **List tasks** (`wrike_list_tasks`, read): List tasks with their status and due dates.
- **Get a task** (`wrike_get_task`, read): Read a task's details.
- **Create a task** (`wrike_create_task`, write): Create a task in a folder or project.
- **Update a task** (`wrike_update_task`, write): Change a task's status, dates or assignees.
- **List folders** (`wrike_list_folders`, read): List the folders and projects in the workspace.
- **List comments** (`wrike_list_comments`, read): Read the comments on a task.
- **Add a comment** (`wrike_add_comment`, write): Comment on a task.

## Limits you can set

**Turn single tools on or off.** Let the agent read tasks and add comments, and switch off `wrike_update_task` so it can never change a task.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example reading the workspace but not editing it. A call outside them is refused.

## Get started

### Step 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.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Wrike

Each end user authorizes their own Wrike account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Wrike account, once.
const connection = await agent200
  .user("user_123")
  .connect("wrike");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Wrike tools

Name the user, the model and the tools. The model decides which Wrike tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "What tasks are due this week in the Website project",
    tools: ["wrike"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Wrike's own sign-in page. You never see or store their Wrike password.

**What access is requested.** The scopes the connection needs, such as reading the workspace or reading and writing it, listed on Wrike's authorization screen. Users can remove the app later from their Wrike account settings.

## Example requests

- "What tasks are due this week in the Website project"
- "Create a task to review the homepage copy by Friday"
- "Mark the launch checklist task as completed"
- "Add a comment that the assets are ready"

## Guides: Wrike with your AI framework

- [Wrike + Claude](https://www.agent200.com/connectors/wrike/framework/claude.md): Set up Wrike for Claude with Agent200, then check which tools are available to your agent.
- [Wrike + ChatGPT](https://www.agent200.com/connectors/wrike/framework/chatgpt.md): Set up Wrike for ChatGPT with Agent200, then check which tools are available to your agent.
- [Wrike + Claude Code](https://www.agent200.com/connectors/wrike/framework/claude-code.md): Set up Wrike for Claude Code with Agent200, then check which tools are available to your agent.
- [Wrike + Muse](https://www.agent200.com/connectors/wrike/framework/muse.md): Set up Wrike for Muse with Agent200, then check which tools are available to your agent.
- [Wrike + Grok Bot](https://www.agent200.com/connectors/wrike/framework/grok-bot.md): Set up Wrike for Grok Bot with Agent200, then check which tools are available to your agent.
- [Wrike + OpenAI Dots](https://www.agent200.com/connectors/wrike/framework/openai-dots.md): Set up Wrike for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Wrike + Claude Duet](https://www.agent200.com/connectors/wrike/framework/claude-duet.md): Set up Wrike for Claude Duet with Agent200, then check which tools are available to your agent.
- [Wrike + Hermes Agent](https://www.agent200.com/connectors/wrike/framework/hermes-agent.md): Set up Wrike for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Wrike + OpenClaw](https://www.agent200.com/connectors/wrike/framework/openclaw.md): Set up Wrike for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Wrike 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 Wrike.

### 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 Wrike connection, never another user's. It cannot reach anything the user or Wrike has not authorized.

### Can I limit what my agent can do in Wrike?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/connectors/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/connectors/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/connectors/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/connectors/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
