Which MCP clients are confirmed to work with notify-completion-mcp-server?
Cline, Claude Desktop, Cursor, and GitHub Copilot have been confirmed to work. Other clients likely work if they have similar capabilities.
@nakat-t
Basic information
The MCP server that provides notifications when AI agents complete long-running tasks. This allows you to leave your desktop without forgetting about tasks.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"notify-completion": {
"command": "npx",
"args": [
"-y",
"@nakat-t/notify-completion-mcp-server@latest"
],
"env": {
"OVERDUE_COMMAND": "<Command to execute very flashy effects>"
},
"autoApprove": [
"start-timer",
"check-overdue"
]
}
}
}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.
The MCP server that provides notifications when AI agents complete long-running tasks, allowing users to leave their desktop without forgetting about tasks. It addresses the issue of users needing to actively monitor their computer for AI task completion by providing a notification mechanism triggered when tasks are finished.
Add the server configuration to your MCP client settings (e.g., cline_mcp_settings.json) using npx, set the OVERDUE_COMMAND environment variable, optionally configure THRESHOLD and EXECUTE_IN_SERVER, and paste the provided custom instructions into your client settings to direct AI agents to call the start-timer and check-overdue tools.
start-timer and check-overdueCline, Claude Desktop, Cursor, and GitHub Copilot have been confirmed to work. Other clients likely work if they have similar capabilities.
`OVERDUE_COMMAND` is required. `THRESHOLD` (default 0 seconds) and `EXECUTE_IN_SERVER` are optional.
The AI agent calls `start-timer` at the beginning of a task and `check-overdue` when the task completes. If elapsed time exceeds the threshold, the server returns the configured command for notification.
The README does not specify any data persistence; timing is handled in-memory during the MCP session.
The README does not specify transport or authentication details.

LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Model Context Protocol Servers
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments