)
Connect monday.com MCP to your AI agents, securely.
One secured endpoint for every monday.com call your AI agents make, scoped per user, inspected, and logged.Try monday.com MCP now
What your agents can ask once monday.com MCP is connected.
“Analyse this board and tell me what is blocked”
“Create an item on the marketing board for this campaign”
“Which items are overdue in this group?”
“Add a comment on this item with the latest status”
“Show the structure of this board”
“List the workspaces I have access to”
Select the tools your AI agents can call
84 tools from the monday.com MCP schema.
Showing 84 tools
What monday.com MCP exposes
monday.com MCP groups its 84 tools into 12 categories, each with a suggested starting policy.
| Category | Covers | Access | Suggested policy |
|---|---|---|---|
| Boards | Board metadata and schema, creation from scratch or templates, activity logs, insights, columns, AI columns, groups and undo | Read / Write | Call get_board_info before any write; audit structural changes |
| Items | Item listing, single and bulk creation, column value changes, moves and delete | Read / Write | Require approval for deletes |
| Updates | Comments and posts on items and boards | Read / Write | Review content before posting |
| Docs & Forms | monday docs, forms and their questions | Read / Write | Review published forms; they collect data from people |
| Workspaces | Workspaces and their contents, folders, moves, dashboards and widgets | Read / Write | Limit organization access |
| GraphQL | Raw GraphQL queries and mutations against the monday.com API | Read / Write | Approve dynamic API calls; they can reach any permitted operation |
| Account & Activity | Users and teams, current user context, notifications, E&A custom activities and timeline items, knowledge base answers and product feedback | Read / Write | Review notifications and feedback before they are sent |
| Files & Assets | Files and assets: upload, retrieval, text extraction and file column updates | Read / Write | Limit uploads and treat file content as potentially sensitive |
| Views | Board views and table views: creation and updates of filters, sorting and settings | Read / Write | Audit view changes; they change what users see on shared boards |
| Object Schemas | Account-level object schemas: listing, creation, updates, deletion, columns and board connections | Read / Write | Require approval for schema deletes and column changes; they propagate to connected boards |
| Automations | Board automations: listing, creation, activation, deactivation, deletion, run history and statistics | Read / Write | Require approval before creating, deleting or reactivating automations |
| monday dev Sprints | monday dev sprints boards, sprint metadata and sprint summaries | Read | Allow read-only reporting |
Connect monday.com MCP to your AI agent
Four steps, under ten minutes.
- 01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
- 02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
- 03
Connect monday.com
Find monday.com in the tool list and connect it.
- 04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.
Permissions down to the single tool
You do not allow monday.com MCP or block it. You allow the exact tools each agent can call, one by one.
| monday.com MCP | 84 TOOLS AVAILABLE |
|---|---|
| Code review agent | 4 tools, read only |
| Issue triage bot | 9 tools |
| Platform team assistant | all 84 tools |
- Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
- Default denyA tool you have not enabled is never exposed to the agent.
- Approval on writesTools that change or delete things can require a human to confirm.
Is monday.com MCP secure?
One endpoint instead of raw credentials. Every call is checked against policy and logged.
| AI agentsConnect through your MCP client configuration. | NeuralTrustApply controls based on your configuration. | monday.com MCP84 documented tools. 3 more dynamic API tools (beta) can be enabled with --enable-dynamic-api-tools. |
|---|---|---|
| Coding assistants | Connection & credentialsper user | Boards16 tools |
| Internal copilots | Tool access policiesdeny by default | Workspaces10 tools |
| Workflow automations | Request & response inspectioninline | Items9 tools |
| Compatible MCP clients | Activity monitoringalerts and logs | All other tools49 tools |
Use monday.com MCP with any AI agent framework
Setup guides for the tools your team already uses.
- Claude CodeSetup guide
- CursorSetup guide
- CodexSetup guide
- WindsurfSetup guide
- Gemini CLISetup guide
- Google AntigravitySetup guide
- GitHub CopilotSetup guide
- Claude EnterpriseSetup guide
- Microsoft Copilot StudioSetup guide
- Open WebUISetup guide
- LangChainSetup guide
- HaystackSetup guide
- Strands AgentsSetup guide
- Vercel AI SDKSetup guide
- n8nSetup guide
Common questions about running monday.com MCP through TrustGate.
Other MCP servers
More servers from the catalog.
Asana
Securely connect your AI agents to Asana through TrustGate: tasks, projects, portfolios, status updates, teams and AI Teammates, scoped per agent and logged.
27 toolsViewLinear
Securely connect your AI agents to Linear through TrustGate: issues, projects, cycles, documents and teams, scoped per agent and logged.
78 toolsViewNotion
Securely connect your AI agents to Notion through TrustGate: pages, databases, comments, files and agent sessions, scoped per agent and logged.
65 toolsView
Connect monday.com MCP instantly
Pick the tools, point your agent at TrustGate, and monday.com MCP is live: scoped, inspected, logged.