Monday.com hosts a remote MCP at mcp.monday.com/mcp that connects AI to your boards, items, and column data through the same API you would use in scripts. With a Monday API token from the developer area, models can list items stuck in a status, create rows from a meeting note, and roll up blockers for a leadership update — all within the permissions of the token’s user.
https://mcp.monday.com/mcp
Claude Sonnet 4.5
Chat with 60+ AI models on the same workflow — switch to a different model mid-conversation and re-run the same prompt, or use Compare mode to put several side-by-side and balance quality vs. cost.
Monday.com API v2 personal token: Avatar → Developers → My access tokens, with access to the workspaces and boards the agent should use.
How models use it and what it is built for.
The Monday.com MCP is built for “non-dev” and ops teams that already keep work in boards. A model can act like a power user: move items through status columns, assign people when your rules allow, and build tabular views of in-flight work. Rate limits and workspace membership still apply, so a token cannot read boards the user is not a member of. In MCP Playground, the Monday template pre-fills the URL so you can focus on scoping the token to the right boards first.
Typical tools an AI model can call. Exact names vary by version.
Copy any of these into MCP Agent Studio after connecting.
Show every item in “Waiting for approval” on my main workspace boards.
Create an item in Marketing: title “Q3 webinar”, due next Friday, assign to Alex.
How many items are Done vs In progress on the Sprint 12 board?
This is not a single-model product: you get the same MCP connection with 60+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.
Default pick for Monday.com
Claude Sonnet 4.5
Claude Sonnet 4.5 handles tabular board data and long status lists well. For quick one-board dumps, try Haiku 4.5; compare in Agent Studio.
Listing tools proves the server is reachable, not that a model can work with it. Evals go further: they read every tool on the server, write a test suite from its real schemas, and run it — code decides pass/fail on the responses (schema conformance, error codes, pagination, result caps) while a scoring model grades plain-English tasks driven through the tools.
Get a pass/fail report per tool with the evidence behind each verdict — and replay the same suite after every schema change. Destructive tools are excluded from the run.
Run evalsOpen MCP Agent Studio with the connection pre-filled. Add your token, pick any of 60+ models, and start chatting — no install required.
Try Monday.com in Agent StudioCommon questions about connecting, scoping and using it safely.
It is a hosted remote MCP that lets AI clients work with your Monday.com boards, items, and columns through Model Context Protocol tools, aligned with the Monday GraphQL/REST style API surface and your user’s access.
In Monday, open the developer or apps area, create a personal access or API token, and restrict it to the workspaces and boards the integration should use. Paste that token into your MCP client as the bearer for mcp.monday.com/mcp.
Only on boards the token can access, and you should still confirm bulk status changes. Use a test board first, and avoid sharing a token with broader workspace admin rights than the workflow needs.
Yes, in clients that support multiple servers — for example you can run Monday with Slack in MCP Agent Studio to summarize work and post a summary. Be mindful of mixing sensitive data across servers.
Claude Sonnet 4.5 is a good default for standup-style rollups. Run the same question against a cheaper model in Compare mode in Agent Studio to see if the extra cost adds accuracy.
Asana
Create tasks, triage projects, and summarise team workload from chat.
Jira & Confluence
Search Jira and Confluence, move tickets, and keep docs aligned with in-flight work — plus JSM, Bitbucket and Compass.
Linear
Triage issues, run cycles and update your product backlog with AI.
Notion
Search, summarise and edit your Notion workspace with AI.