Monday.com MCP for AI. Manage tasks and boards without leaving your chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Monday.com MCP Server connects your AI client to your entire Work OS. It lets you manage projects, assign tasks, and read team data without logging into the dashboard.
Your agent can list all boards in a workspace, create new items, update specific column values, or post comments—all through natural language conversation.
What your AI can do
Create new item
Adds a new row (task) to a specific board, allowing you to define initial column values.
Post item update
Adds a new comment or status update to an existing task item's feed.
Remove item
Deletes an entire row (task) from the board, removing it from circulation.
List all boards, workspaces, or groups within your Monday.com account.
Create new tasks on a board; update existing task columns; or delete entire items.
Add comments to specific items, or retrieve the full history of updates for a task.
Fetch schema details (column types) for a board, or list all team members and user profiles.
Ask an AI about this
Waiting for input…
Monday.com MCP Server: 12 Tools for Board Operations
These twelve tools give your AI agent full control over reading, writing, updating, and managing every core element of your Monday.com workspace.
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 Monday.com on VinkiusCreate New Item
Adds a new row (task) to a specific board, allowing you to define initial column values.
Post Item Update
Adds a new comment or status update to an existing task item's feed.
Remove Item
Deletes an entire row (task) from the board, removing it from circulation.
Get Board Schema
Retrieves the names and types of all columns available on a selected board.
Get My Profile
Fetches basic information about the connected Monday.com user account.
List Boards
Retrieves an overview of every available board in your workspace.
List Board Groups
Retrieves the names of sections or groups that organize items on a board.
List Board Items
Lists all rows (tasks) belonging to a specific Monday.com board.
List Item Updates
Gets a chronological list of all comments and updates made to a specific task item.
List Account Users
Lists all team members and their associated profiles within your workspace.
List Workspaces
Lists the main container or umbrella projects within your overall Monday.com account.
Update Item Columns
Modifies one or more specific values within a task item's columns.
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 Monday.com 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 Monday.com, 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 Monday.com. 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 connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Checking task status shouldn't require navigating three separate tabs.
Today, checking on project progress means logging into Monday.com, finding the correct board, scrolling through groups, and hunting for specific items to see who last worked on them—it’s a multi-step process that kills momentum.
With this MCP server, you just ask your agent: 'What's the status of the Q4 Roadmap?' The tool runs `list_board_items` or `list_item_updates`, and it spits out the answer in chat. You get the data without ever leaving your conversation.
Monday.com MCP Server: Automate board changes via natural language
The manual steps that vanish? Clicking into a task, finding the 'Status' column dropdown, selecting the new value (e.g., 'In Review'), and then hitting save. That sequence is slow, tedious, and error-prone.
Now, you just tell your agent: 'Change the status of Item 456 to In Review.' The server executes `update_item_columns` in a single, atomic step. It's immediate, precise, and keeps a record.
What your AI can actually do with this
Your agent handles everything in Monday.com, letting you manage your entire Work OS straight from chat. You don't gotta log into the dashboard; just talk to your client and get things done.
Discovering Your Workspace Structure
You can start by listing all your main containers, which are the list_workspaces umbrella projects. From there, you'll see every available board using list_boards. For any single board, your agent gets the names of all organizational sections with list_board_groups. To know what data points a board uses, run get_board_schema, and it’ll pull back the exact column names and their types.
You can list every row (task) on a specific board using list_board_items.
Managing Tasks (Items)
When you need to make changes, your agent handles the whole lifecycle. To get started, you'll use create_new_item, telling it which board to add the task to and what initial column values should be set. Need to change something later? You modify existing data using update_item_columns by specifying which columns need new values for a given item.
If an entire row is dead weight, you can trash it completely with remove_item.
Communication and Tracking Updates
You keep everyone in the loop through updates. You can post a fresh comment or status update to any task using post_item_update for instant transparency. If you gotta check what happened last week, your agent retrieves the full history of comments and changes made on that item via list_item_updates.
Getting Core System Data
Your client also gives you visibility into who's working on what. It pulls basic details about your connected account using get_my_profile, and it can list every teammate in the workspace, fetching all profiles with list_account_users.
019dd127-c417-7359-bfc5-be0550b58e56 
Here's how it actually works
The bottom line is, you use your agent like a dedicated operations assistant that talks directly to Monday.com's backend.
Subscribe to the MCP Server and generate an API token.
Input your Monday.com API Token into the server configuration.
Ask your AI client (e.g., 'List all active project boards') to begin managing data.
Who is this actually for?
Project Managers and Operations Engineers who are tired of context-switching between the chat window and multiple dashboard tabs need this. It’s for anyone whose job involves tracking project status or assigning tasks across a complex, multi-board setup. You get to keep working in your agent's chat interface.
Needs to quickly list all active boards and check the current task health for multiple projects without navigating away from their communication tool.
Automates the creation of tasks or updates board data across departments simply by describing the desired change in natural language.
Needs to fetch real-time project metadata and user profiles directly within a development chat to keep technical roadmaps synchronized.
What Changes When You Connect
Stop switching apps to check status. Use list_board_items or get_board_schema to pull live project data directly into the conversation.
Assign work instantly. The create_new_item tool lets you generate a task and define its initial column values without opening Monday.com.
Keep communication centralized. Use post_item_update to add comments or status changes to a task right from your agent, keeping the record clean.
Track history accurately. If you need context, run list_item_updates to pull the full comment thread for any item, instantly.
Manage team structure easily. Run list_account_users whenever you need to know who's on a board or what roles are available.
See it in action
The Status Check
A Project Manager needs to know if the 'Marketing Launch' task is approved. Instead of navigating to the board, they prompt their agent: 'Show the latest updates for the Marketing Launch item.' The agent runs list_item_updates and reports the final comment directly in chat.
New Task Creation
An Operations Coordinator is told to create three new tasks. They prompt: 'Create a task for SEO Audit, assign it to John, and set the status column to 'To Do'.' The agent uses create_new_item and handles all necessary data mapping.
Board Discovery
A new team member starts and needs to know what projects are active. They ask: 'What boards do we use for Q4 planning?' The agent runs list_boards, providing a clean, actionable list of environments.
Data Correction
A developer realizes the wrong date was entered into a task. Instead of opening the board editor, they prompt: 'Update the deadline column for Item XYZ to 2024-12-31.' The agent runs update_item_columns safely.
The honest tradeoffs
Trying to process data manually
Copying item IDs, then opening the board, finding the right column header, and pasting it into a spreadsheet. This takes minutes and breaks easily.
Use the agent's metadata tools. First, run get_board_schema to get all column names, then use list_board_items to get the raw data payload—all in one conversation.
Over-relying on memory
Forgetting which specific board ID or item key you were working with; having to search through your entire workspace.
Always start by running list_boards to confirm the exact names and IDs. This gives your agent the precise context it needs for subsequent calls.
Assuming data is always fresh
Running a report that shows status 'Complete,' only to find out later that another user posted an update minutes after the initial read.
If real-time accuracy matters, run list_item_updates first. This ensures you are reading the most recent comments and activity before making any decisions or updates.
When It Fits, When It Doesn't
Use this server if your process is built around discrete steps: 'First, find all boards; second, list items on board X; third, update column Y for item Z.' You need a controlled sequence of reads and writes. Don't use it if you are trying to model complex, interconnected data flows across entirely different platforms (e.g., connecting Monday.com task status directly to Salesforce revenue figures). For that, you'll need an enterprise integration layer or middleware tool. This server excels at deep CRUD operations within the Monday ecosystem; it doesn't resolve cross-platform dependencies. It’s a powerful local coordinator, not a global pipeline builder.
Questions you might have
How do I use the list_boards tool with Monday.com MCP Server? +
Simply ask your agent to 'list all boards in my workspace.' The server runs list_boards and returns a categorized list of every available environment, which is necessary before targeting any specific tasks.
Can I use create_new_item for multiple projects? +
You must specify the target board ID or name. The create_new_item tool only adds a row to one defined location at a time, so you'll need to issue separate commands for different boards.
What is the difference between list_board_items and list_workspaces? +
The difference is scope. list_workspaces shows your highest-level project containers, while list_board_items gets you to the specific rows (tasks) within a single board.
Does post_item_update log who added the comment? +
Yes. The update mechanism tracks authorship and timestamps. When using post_item_update, you're adding a comment that is logged alongside other user contributions to maintain project history.
Before I run `update_item_columns`, how do I confirm what data type a column needs to be? +
You must run the get_board_schema tool first. This function returns all board metadata, showing you exactly whether a column expects text, numbers, or dates. Always check the schema before attempting an update.
If I use `remove_item`, is there any way to undo the deletion of a board row? +
No, removing an item via this tool is permanent and cannot be recovered through the API. Always verify the specific Item ID before running remove_item on critical data.
What happens if I run `list_item_updates` for a highly active board? +
High volumes of read requests can hit API rate limits. If you need history across many items, you should consider batching your reads or checking the specific usage quota documentation.
How does `get_my_profile` behave if I'm trying to check another user’s information? +
It uses the API token owner's context by default. To get details for a different team member, you need to pass that specific user ID into the function call.
Can my AI automatically find the details for a specific item by its ID? +
Yes! Use the get_item_details tool (via queries). Your agent will respond with complete metadata for the record, including column values and update history in seconds.
How do I find my Monday.com API Token? +
Log in to your Monday.com account, click on your Avatar (bottom left), navigate to Developers, and you will find your unique secret token under the API section.
Does this work with private boards? +
Yes, provided the API token used has the necessary permissions and access to those boards within your Monday.com workspace.
Powerful workflows you can unlock today
MCP Servers for Async Standups Without Meetings
Your 15-minute daily standup takes 45 minutes because everyone reads their Monday.com board out loud , and the remote team in Sao Paulo missed it because the Zoom link expired
MCP Servers That Turn Forms Into Tasks
Form submitted, project task created, client notified on WhatsApp , intake to kickoff without a single email
We've already built the connector for Monday.com. 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.