Wrike MCP for AI. Automate project tracking and team ops.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Wrike MCP connects your AI agent directly into Wrike for enterprise project management. Manage complex workflows by listing tasks, creating new projects, tracking team comments, and updating task statuses automatically through natural language conversation.
What AI agents can do with Wrike Automation
Add task comment
Post comment to task
Create folder
Add new folder/project
Create task
Add new task
Ask an AI about this
Waiting for input…
What AI agents can do with Wrike: 12 Tools for Project Management
Use these twelve tools to control every aspect of your Wrike workspace, from creating new folders and projects to updating task status and listing team members.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Wrike on VinkiusAdd Task Comment
Post comment to task
Create Folder
Add new folder/project
Create Task
Add new task
Get User Profile
Get current user
Get Task Details
Get full task info
List Task Comments
Get task discussion
List Team Members
List workspace users
List Task Attachments
List task files
List Folders And Projects
List hierarchy
List Tasks
Can filter by status (Active, Completed, Deferred, Cancelled). List project tasks
List Custom Workflows
List task workflows
Update Task
Modify task info
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Wrike integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Wrike, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Wrike. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The endless cycle of context switching and manual updates.
Today, managing a project means jumping between Wrike's task views, checking email threads for decisions, opening the file repository to find attachments, and then going back to the main task card just to update the status. You spend half your day copying details from one place to another or hunting down who made that initial decision.
With this MCP, you talk to your agent instead of clicking through seven different tabs. The agent pulls all necessary information—the discussion history via `list_task_comments`, the required files using `list_task_attachments`, and the current status on a single task—and presents it to you immediately.
Get full visibility into project data with the Wrike MCP.
The agent handles the tedious work of compiling reports. You can ask it to list all tasks across multiple projects and then, in one step, update their priority or assign them to a new person using `update_task` and `list_tasks`.
What's different now is that you control the process flow through conversation. You don't just look at data; you manipulate it—you create tasks, you build folders, you move projects forward.
What your AI can actually do with this
This connector lets you manage massive, structured projects without opening the Wrike app. Instead of navigating folders, clicking dropdowns, and manually copying status updates, you talk to your agent. You can ask it to list all tasks assigned to a specific team member or create an entirely new project folder for a client kickoff.
Need to update something? Just tell the agent to change a task's priority or assign it to someone else. Because Wrike handles everything from high-level organizational structure to granular file attachments, your AI agent can manage the whole lifecycle. If you need to build automations that span multiple platforms—say, creating a task in Wrike and then sending a notification about it through a messaging service—you can chain Wrike with other MCPs using Vinkius.
This means building entire automated workflows right from your single connection point.
019dd18b-af34-7379-85c0-acbc08352a4b 
Here's how it actually works
The bottom line is you get centralized control over complex project data without ever leaving your AI client interface.
Subscribe to this MCP and provide your Wrike Permanent Token.
Connect your AI client; it validates the token and sets up a secure, zero-trust connection.
Ask your agent a question—for instance, 'List all tasks in the Marketing department folder that are overdue.' — and the agent executes the necessary calls.
Who is this actually for?
Project Managers, Operations Leads, and Team Coordinators. These are the people who wake up knowing that scattered data across spreadsheets, email chains, and multiple platforms is going to cause a project delay if they don't get a clear, single source of truth.
You use this agent to monitor progress across dozens of client projects, getting instant reports on who needs what and why.
You rely on it to enforce standardized workflows, ensuring every task gets the right metadata assigned before moving forward.
You use it to keep team members aligned by programmatically retrieving and posting discussion threads directly to tasks.
What Changes When You Connect
Instead of clicking through multiple tabs to see if a task is ready for review, you can simply ask the agent to list tasks with status 'Pending Review' using list_tasks.
Need to start a new client initiative? You don't build a project from scratch. Just tell your agent to use create_folder, and it builds the container instantly.
When team members make decisions, all key discussion points get captured in one place. Use add_task_comment to keep the record clean and traceable.
If you need to track down who owns a project or what files are attached, calling get_task_details gives you the full picture instantly.
You can programmatically enforce status changes by having the agent run update_task, ensuring that no task skips a required step before being marked complete.
See it in action
The weekly project health check
A Project Manager asks their agent: 'List all active tasks for Q3 that are assigned to the Marketing department and haven't been updated in ten days.' The agent runs list_tasks and filters by date, immediately showing bottlenecks.
Onboarding a new client
An Operations Lead tells their agent: 'Create a new folder for Client X, set the initial tasks, and assign it to John.' The agent uses create_folder followed by multiple create_task calls.
Retrieving decision history
A Team Coordinator needs to know why a feature was paused. They ask the agent to pull all comments using list_task_comments for that task, instantly giving them the full discussion thread.
Auditing team roles
Before granting access to sensitive project data, an Admin asks the agent to list all current users via list_team_members, verifying who needs specific permissions.
The honest tradeoffs
Manual status updates
A team member completes work and has to manually change the task from 'In Progress' to 'Ready for Review,' then emails a screenshot of the change.
Just tell your agent: 'Update the task status to Ready for Review.' The agent runs update_task directly, changing the status without any extra clicks or emails.
Losing track of files
A PM can't find the final mockups because they were attached weeks ago and aren't listed on the main task page.
Ask your agent to run list_task_attachments for that task. It pulls a clean list of all associated files, so you never lose track of required assets.
Over-complicating folder structure
Trying to manually create deep, nested folders and projects just by clicking through the UI for every client.
Tell your agent: 'Create a new top-level project called Beta Launch.' The agent uses create_folder and sets up the entire container in one step.
When It Fits, When It Doesn't
Use this MCP if managing projects means juggling multiple discrete pieces of data—tasks, files, people, statuses. You need a system that can read status updates via list_tasks, track conversations using add_task_comment, and enforce process changes with update_task. Don't use this if you only need to store simple contact lists or manage one-off documents; those are better suited for dedicated CRM tools. If your primary goal is simply viewing a calendar, an embedded scheduling tool works better. This MCP excels at the connective tissue of enterprise workflow.
Questions you might have
How do I list my active Wrike project tasks using the `list_tasks` tool? +
You simply tell your agent: 'List all active tasks due this week.' The agent uses list_tasks and applies filters for status (Active) and date range, giving you a clean, filtered report.
Can I add notes to an existing task using the Wrike MCP? +
Yes, just tell your agent to use add_task_comment. You don't have to open the task card; you just provide the comment and the agent posts it for you.
What is the best way to create a new project folder? Should I use `create_folder`? +
Yes, using create_folder works perfectly. Just tell your agent: 'Create a new folder named Q4 Budget Review.' The agent handles the structure creation immediately.
I need to check who is on my team. How do I use `list_team_members`? +
Ask the agent directly: 'List all team members in this workspace.' It runs list_team_members and returns a current roster of active users.
I need more than just the title when I create a task. How do I get full details, like custom metadata, using `get_task_details`? +
It retrieves all available information about any given task. This means you can pull not only the status and priority but also specific custom fields or metadata attached to it. It’s perfect for building comprehensive records without having to guess what data is missing.
I want to change both a task's status and its assigned owner simultaneously. Can I use `update_task`? +
Yes, you can modify multiple fields with a single call using update_task. You don't have to run separate actions for each piece of information. This makes updating complex records much faster and more reliable.
I need to see what automated rules are available for tasks. How do I use `list_custom_workflows`? +
This tool lists all the pre-defined custom workflows associated with your Wrike account. It lets you see exactly what automation processes exist, giving you a full view of how task progression is managed across your organization.
A task has several files attached to it. How do I list and access those related documents using `list_task_attachments`? +
The tool lists all the physical files linked to a specific task ID. You get the necessary file IDs, which you can then pass to another function (or your agent) to retrieve the actual content. It's how you manage all supporting documentation in one place.
What is the difference between Folders and Projects in Wrike? +
In Wrike, a Project is technically a Folder with added metadata such as owners, start/end dates, and project-specific statuses to help track deadlines and responsibility.
Can I move a task to a different project via AI? +
Yes, you can use the update_task tool and provide the addParents or removeParents parameters in the attributes to change which project or folder the task belongs to.
We've already built the connector for Wrike. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.