Asana MCP. Query and manage your project data via AI agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Asana MCP lets your AI agent manage and query project workflows directly from Asana. It allows you to list workspaces, find specific projects, check task status, and even create or update tasks using natural conversation.
Stop opening dozens of tabs just to figure out who owns a deliverable.
What your AI agents can do
Add task comment
Adds a comment to an existing Asana task for team communication.
Create task
Generates and adds a brand new task into the system.
Delete task
Removes a specified Asana task permanently from the workspace.
You can pull lists of all workspaces and projects within an organization's structure.
Fetch detailed information about any specific task, checking its full history, assignee, and current status.
Create new tasks, update existing details, or add comments to keep projects moving forward.
Retrieve user profiles and specific organizational credentials used within Asana.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Asana: 15 Tools for Project Mastery
Use these tools to execute everything from creating a new task with `create_task` to searching complex project data with `search_tasks`.
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 Asana on Vinkius019eb86eadd task comment
Adds a comment to an existing Asana task for team communication.
019d7552create task
Generates and adds a brand new task into the system.
019eb86edelete task
Removes a specified Asana task permanently from the workspace.
019d7552get me
Retrieves the profile and access details for your connected Asana user account.
019d7552get task
Fetches all detailed information for a single, specific task ID.
019eb86eget user
Gets the profile details and credentials for any specified Asana user.
019eb86elist portfolios
Lists all defined portfolios within a given workspace structure.
019d7552list projects
Retrieves a list of active projects belonging to the current workspace.
019d7552list sections
Lists all board column groupings or stages (sections) inside an Asana project.
019d7552list stories
Fetches the chronological activity feed, or 'stories', for a task.
019d7552list tags
Retrieves all available tags used across the entire workspace.
019d7552list tasks
Lists multiple tasks within an Asana project based on general criteria.
019d7552list workspaces
Retrieves a list of every organizational workspace you have access to.
019d7552search tasks
Searches for tasks across the entire workspace using specific filters and criteria.
019d7552update task
Modifies attributes of an existing task, such as status or assignee.
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 Asana, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 Asana. 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
Works with 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 server provides 15 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The old way means opening tabs, refreshing screens, and asking people 'Are you there?'
Today, tracking a project's actual health feels like detective work. You jump into Asana, check the main board, then open related projects in new tabs to see if they are linked. If you need to know who owns the next step, you have to manually click on every task and read through the comments. It’s slow, it's prone to human error, and you spend half your day just *gathering* data.
With this MCP connected via Vinkius, you tell your agent exactly what you need—for example, 'Show me all tasks assigned to Sarah in Marketing that haven't been updated since last week.' You get a clean, filtered list instantly. Your AI acts as the dedicated research assistant who never needs coffee breaks.
List projects and workspaces with Asana MCP
Before this MCP, figuring out which teams were working on what involved a lot of asking around. You had to open multiple departmental accounts or manually scroll through large lists just to get an overview of the available work environments.
Now you simply ask your agent to use `list_workspaces`. It pulls the entire organizational map into your conversation window, showing every possible project area at once. It’s a single command that replaces ten clicks.
What you can do with this MCP connector
Connect your organizational account to any AI client and treat it like a dedicated project manager for Asana. You get full control over the data; you don't have to navigate the app interface yourself. Your agent reads everything—from listing all workspaces to finding deep metadata on individual tasks, including who is assigned and what status they're in.
If you’ve been looking at Vinkius for a way to connect project management into your daily workflow, this MCP lets your AI handle it entirely through conversation. You can check progress across entire portfolios, list board sections to understand the sprint stages, or even initiate actions like creating a new task when a requirement comes up.
019d7552-e202-7165-a3ea-79751afa7d52 
How Asana MCP Works
- 1 First, subscribe to this MCP on Vinkius and enter your Asana Personal Access Token.
- 2 Next, prompt your AI agent with a request like 'List all active projects in the Marketing workspace.'
- 3 The agent executes the call and returns structured data detailing everything you need to know about those projects.
The bottom line is that once connected, your AI client handles the API calls so you don't have to worry about tokens or endpoints.
Who Is Asana MCP For?
This MCP is for Product Managers and Engineering Leads who spend too much time context-switching between project boards and chat tools. If you need real-time status checks or data extraction, this saves the clicking.
You check if a feature is blocked by listing tasks that are stale or inspecting sections to see where the sprint board stalled.
You track cross-functional progress by querying multiple workspaces and confirming which team members own specific deliverables.
You grab a task description or metadata directly from your IDE to ensure the code fix matches the original requirement without leaving your coding environment.
What Changes When You Connect
- Instead of opening the Asana app to check status, you can simply ask your agent to run
search_tasksacross a workspace for tasks tagged 'Urgent' that are assigned to Marcus R., getting instant results. - You don't need multiple tabs open. You can use
list_workspacesfirst to identify the right project environment, then drill down usinglist_projectsbefore focusing on individual items withget_task. - Need to update something? Instead of manually navigating through settings, your agent uses
update_taskoradd_task_commentto make changes and log them immediately. - Checking team credentials is easy. Use
list_sectionsto understand the flow (e.g., 'To Do' -> 'In Progress') and then useget_userto see who owns each stage. - Forget clicking through boards just to list what needs work. Your agent can call
list_tagsor perform a comprehensive search usingsearch_tasks, giving you the full picture instantly.
Real-World Use Cases
The status check for an upcoming launch.
A Project Lead needs to know if all key tasks are on track. They ask their agent, 'What's the status of our Q3 marketing deliverables?' The agent runs multiple queries using list_tasks and get_task, compiling a report that identifies which specific deliverable is stuck in an unassigned section.
Onboarding a new team member.
An Operations Manager needs to see what resources the new hire can access. They prompt their agent with, 'Show me all available project groups.' The agent uses list_workspaces and then list_projects, providing the manager a clear map of potential work areas.
Correcting an outdated requirement.
A Developer spots an error in the requirements document. They ask their agent to 'Get all details for task GID 12039402123.' The agent uses get_task to retrieve the metadata, allowing the developer to confirm the original scope before coding.
Archiving old project work.
A Scrum Master needs to clean up a completed sprint. They use their agent to first list all sections in the project using list_sections, then identify tasks that are complete, and finally call delete_task on the obsolete items.
The Tradeoffs
Assuming task status is visible.
Manually checking a project board only shows the 'In Progress' column. If the assignee hasn't moved it, you assume nothing happened and miss actual blockers.
→
Ask your agent to use search_tasks with filters for both status AND last modified date. This confirms if the task was genuinely updated or just left sitting there.
Trying to find a user's current role.
Searching through emails and internal documents to figure out who is responsible for a deliverable, wasting time cross-referencing names and roles.
→
Use get_user or get_task on the specific task. The agent immediately pulls the assigned user's profile details, cutting straight to the answer.
Updating a task without logging it.
Changing a status directly in the app and assuming teammates know why or when it happened, leading to confusion later.
→
After using update_task, always prompt your agent to call add_task_comment first. This logs the change and provides context for everyone else.
When It Fits, When It Doesn't
Use this MCP if your workflow requires programmatic interaction with project state, not just viewing it. You need to know the 'who' and 'why', not just the 'what'. For instance, if you want a list of all potential projects across departments, use list_workspaces followed by list_projects. If you only care about finding one specific thing, search_tasks is better than list_tasks. Don't try to build dependency graphs; this MCP handles discrete CRUD operations. If your goal is pure visualization or reporting into a BI tool, that might require an external data connector instead. But for real-time action and deep querying within Asana itself—this is the right fit.
Common Questions About Asana MCP
How do I check task status using get_task? +
The agent uses get_task to pull the full metadata for any given task ID. This returns its exact current status, who it's assigned to, and a complete history of activity stories.
Can I create tasks using create_task? +
Yes. You can use create_task by giving the agent enough detail in your prompt—such as the title, description, and assignee—and it handles generating the record inside Asana.
Does search_tasks work better than list_tasks? +
Generally, search_tasks is more powerful. It allows you to apply multiple filters (like date range or specific tags) at once, whereas list_tasks provides a broader but less targeted listing.
How do I add comments using add_task_comment? +
You pass the task ID and your comment text to the agent. It then executes add_task_comment, ensuring the record is updated with a clear, time-stamped note.
Is deleting a task permanent when I run the `delete_task` command? +
Yes, deletion is immediate and irreversible. The API executes the removal instantly; make sure you've backed up any critical details before sending the delete request.
How do I find out which workspaces are available using `list_workspaces`? +
The list_workspaces tool fetches every organizational environment your agent has access to. It's the ideal first step when you need to know the scope of all possible projects and teams.
What kind of data changes can I make with the `update_task` function? +
You can modify an existing task’s status, assignee, description, or due date. Just pass a payload with the new structured data to change the work item's metadata.
How do I verify my agent's current API user credentials using `get_me`? +
get_me returns your system's profile information and authorized access details. Use this tool to confirm the exact identity your MCP is operating under for auditing purposes.
Multi-server workflows that include Asana MCP
Identify Unprofitable Agency Clients Using MCP
Your biggest client generates 28% of revenue but consumes 45% of your team's time , and you will not know they are your least profitable account until you compare project hours against deal value, which nobody does because the data is in 3 different tools
Never Miss a Project Deadline Using MCP
Three deadlines passed last week and nobody noticed because the Asana due dates do not sync to calendars and email reminders go to a folder nobody reads
Ship Design Handoffs Smoothly Using MCP Servers
Design files reviewed, dev tasks created and team notified , one conversation, zero handoff meetings
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.