What is the difference between hosted and local MCP?
Hosted MCP is recommended for most users – it requires no local setup, updates automatically, and uses OAuth. Local MCP allows customization, offline use, and direct source code modifications.
@mondaycom
Basic information
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-mondaycom": {
"command": "npx",
"args": [
"@mondaydotcomorg/monday-api-mcp@latest",
"--enable-dynamic-api-tools",
"true"
],
"env": {
"MONDAY_TOKEN": "your_monday_api_token"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
It is an open framework that connects AI agents to the monday.com work operating system, providing secure access to structured data and tools for actions. Maintained by monday.com's AI team, it is available as a hosted service or a local server.
Use the hosted MCP by adding its URL to your MCP client configuration, or install locally by generating a monday.com API token and configuring the client (e.g., Claude Desktop) with the npx command and MONDAY_TOKEN environment variable. For Gemini CLI, install the extension and authenticate via /mcp auth monday.
Hosted MCP is recommended for most users – it requires no local setup, updates automatically, and uses OAuth. Local MCP allows customization, offline use, and direct source code modifications.
Local installation requires Node.js v20 or higher and a monday.com API token. The server runs via the `npx @mondaydotcomorg/monday-api-mcp@latest` command.
Hosted MCP uses OAuth authentication and optional workspace controls. Local MCP uses a personal API token generated from your monday.com developer settings, passed as the `MONDAY_TOKEN` environment variable.
Yes, the README documents integrations with Claude Desktop, ChatGPT, Cursor, Microsoft Copilot Studio, Mistral AI's le Chat, and Gemini CLI (via extension or direct MCP addition).
Dynamic API Tools are in Beta and provide full GraphQL API access. The hosted MCP is recommended for higher reliability and performance. No other specific limits are mentioned in the README.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
A search tool helps dev to solve the naming things problem.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Comments