- Home
- MCP servers
- Mondaycom
Mondaycom
- typescript
380
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You can connect AI agents to monday.com through a dedicated MCP server that provides secure access to your data and actions, enabling reliable operation within real workflows while leveraging monday.com APIs and tools.
How to use
Use the MCP server to let your AI assistants interact with monday.com data and perform actions such as creating items, updating boards, and querying board items. You can connect via a hosted MCP service for instant setup or run a local MCP server for customization and offline development. When using a client, you choose an MCP server URL or a local runtime, then authenticate with your monday.com API token to access supported tools and features.
How to install
Prerequisites you need before installation:
-
Node.js v20+ is required
-
NPM v5.2.0+ is required
-
Obtain a personal access token from monday.com
Recommended steps to start using the MCP locally or with a client:
# Local MCP with dynamic API tools enabled
MONDAY_TOKEN=your_monday_api_token npx @mondaydotcomorg/monday-api-mcp@latest --enable-dynamic-api-tools true
Configuration and usage notes
Hosted MCP is the fastest and most robust option for connecting to monday.com. It handles infrastructure, updates, security, and uptime, so you can focus on building AI workflows.
If you prefer to run MCP locally or customize the server, you can run the MCP server using the provided runtime for local development. Be sure to set your monday.com API token in the environment.
Examples of how to connect from a client: you can configure your MCP client to point to either the hosted MCP URL or your local MCP runtime, and then authenticate with your monday.com token to access tools and capabilities.
Security, tokens and access control
Authenticate with a monday.com API token and consider enabling read-only mode if you only need to retrieve data. Regularly rotate API tokens and limit workspace access to reduce risk.
Example setup for a client like Cursor
Add the hosted MCP server to your MCP settings in Cursor with this configuration snippet.
{
"mcpServers": {
"monday-mcp": {
"url": "https://mcp.monday.com/mcp"
}
}
}
Testing your integration
Ask your assistant questions such as “What items exist in board 123?” or “Can you create a board to manage my project?” to verify that it can interact with your monday.com data and perform actions through the MCP server.
Notes on advanced usage
Dynamic API Tools are in beta and disabled by default. Enable them to grant your AI agents full GraphQL API access when needed, or use the exclusive mode to work solely with Dynamic API Tools for advanced scenarios.
Available tools
create_item
Create a new item in a board with specified column values
delete_item
Delete an item from a board permanently
get_board_items_by_name
Search for items on a board by name or term
create_update
Add an update or comment to a specific item
change_item_column_values
Modify the column values of an existing item
move_item_to_group
Move an item to a different group within the same board
create_board
Create a new board with specified columns
get_board_schema
Retrieve the structure of columns and groups for a board
create_group
Create a new group on a board
create_column
Add a new column to a board
delete_column
Remove a column from a board
list_users_and_teams
Retrieve user or team details by id or name
create_form
Create a new monday.com form
get_form
Get a form by its token