High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
MCP server for Pushover notifications
This repository provides an MCP server that connects an agent to Pushover.net. The agent can call a single `send` tool to post a notification with a message, optional title, priority, sound, URL, and target device.
Builders who want their agent to send push notifications through Pushover while they build.
You can get notified by your agent without leaving your coding workflow.
What it does
Send notifications
Implements a `send` MCP tool for posting Pushover messages.
Message options
Supports optional title, priority, sound, URL, URL title, and device fields.
Cursor setup
Shows how to add the server in Cursor with a command or project MCP config.
Smithery install
Includes a Smithery command for installing the server for Claude clients.
How to get it
- 1Run the MCP server using npx
npx -y pushover-mcp@latest start --token YOUR_TOKEN --user YOUR_USER
README
Pushover MCP
A Model Context Protocol implementation for sending notifications via Pushover.net.
Overview
This MCP enables AI agents to send notifications through Pushover.net. It implements the MCP specification, allowing seamless integration with MCP-compatible AI systems.
Configuration
You'll need:
- An application token from Pushover.net
- Your user key from Pushover.net
Get these from your Pushover.net dashboard.
Tool Schema
The MCP provides a single tool:
send
Sends a notification via Pushover.
{
message: string; // Required: The message to send
title?: string; // Optional: Message title
priority?: number; // Optional: -2 to 2 (-2: lowest, 2: emergency)
sound?: string; // Optional: Notification sound
url?: string; // Optional: URL to include
url_title?: string; // Optional: Title for the URL
device?: string; // Optional: Target specific device
}
Example MCP Tool Call
{
"name": "send",
"params": {
"message": "Hello from AI",
"title": "AI Notification",
"priority": 1
}
}
Installing
Using with Cursor
Method 1: Install Globally
Run the MCP server using npx:
npx -y pushover-mcp@latest start --token YOUR_TOKEN --user YOUR_USER
In your Cursor IDE
- Go to
Cursor Settings>MCP - Click
+ Add New MCP Server - Fill in the form:
- Name:
Pushover Notification(or any name you prefer) - Type:
command - Command:
npx -y pushover-mcp@latest start --token YOUR_TOKEN --user YOUR_USER
- Name:
Method 2: Project-specific Configuration
Add an .cursor/mcp.json file to your project:
{
"mcpServers": {
"pushover": {
"command": "npx",
"args": [
"-y",
"pushover-mcp@latest",
"start",
"--token",
"YOUR_TOKEN",
"--user",
"YOUR_USER"
]
}
}
}
Using the Tool
Once configured, the Pushover notification tool will be automatically available to the Cursor AI Agent. You can:
- The tool will be listed under
Available Toolsin MCP settings - Agent will automatically use it when relevant
- You can explicitly ask Agent to send notifications
By default, Agent will ask for approval before sending notifications. Enable "Yolo mode" in settings to allow automatic sending.

Using with Roo Code
Access the MCP settings by clicking “Edit MCP Settings” in Roo Code settings or using the “Roo Code: Open MCP Config” command in VS Code's command palette.
{
"mcpServers": {
"pushover": {
"command": "npx",
"args": [
"-y",
"pushover-mcp@latest",
"start",
"--token",
"YOUR_TOKEN",
"--user",
"YOUR_USER"
]
}
}
}
- The Pushover notification tool will be available to Roo Code's AI agents
Note: Replace
YOUR_TOKEN&YOUR_USERwith your Pushover credentials.
Installing via Smithery
To install Pushover Notification for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @AshikNesin/pushover-mcp --client claude
Development
# Install dependencies
pnpm install
# Build
pnpm build
# Run tests
pnpm test
License
MIT
Files in the repo
- media
- src
- .gitignore
- Dockerfile
- LICENSE
- package.json
- pnpm-lock.yaml
- README.md
- smithery.yaml
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。