MNotify MCP Server
Enables AI IDEs like Cursor to send SMS, manage contacts/groups/templates, and check delivery reports via the MNotify API through natural language tool calls.
README
MNotify MCP Server
Bring MNotify to your AI IDE in one command.
This package exposes the MNotify SMS API as an MCP server so tools like Cursor can securely call real MNotify actions (send SMS, manage contacts/groups/templates, delivery reports) via stdio. This repo also includes a simple interactive MNotify Agent for CLI use. It is based on Mnotify API v2.0
Check out the PyPI MCP package here
Requirements
- Python 3.10+
- Environment variable:
MNOTIFY_API_KEY
Setup
- Using uv (recommended):
curl -LsSf https://astral.sh/uv/install.sh | sh # install uv if needed uv venv uv pip install -r requirements.txt - Using any virtualenv manager + pip:
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt
Quick start — install and run the MCP server
pip install mnotify_mcp_server
export MNOTIFY_API_KEY=sk_mnotify_...
# Start the server (preferred)
mnotify_mcp server
# Alternatives
mnotify-mcp
python -m mnotify_mcp.server
Connect to Cursor
- Option A: Project config
.cursor/mcp.json(recommended)
{
"mcpServers": {
"mnotify": {
"command": "mnotify_mcp",
"args": ["server"]
}
}
}
Relaunch cursor from the same environment as the virtual environment
- Option B: Manual add in Cursor (Settings → MCP → Add Custom Server → Process)
- Command:
mnotify_mcp - Args:
server - Ensure
MNOTIFY_API_KEYis set in the environment where Cursor launches the process
- Command:
MNotify Agent (interactive CLI)
A local chat agent that can call all MNotify tools directly.

Setup
- Create a virtual environment and install dependencies with uv or pip (see above).
- Add a
.envfile with:
OPENROUTER_API_KEY=sk-or-v1-...
MNOTIFY_API_KEY=...
AGNO_API_KEY=ag-... # optional, if monitoring is set.
Start the agent
uv run mnotify_agent.py
CLI commands
- help: list commands
- history: show recent messages
- tools: list available tools
- test: run a quick tool-call test
- clear: clear conversation context
Tools exposed
- SMS:
send_quick_bulk_sms,send_bulk_group_sms,update_scheduled_sms - Reports:
sms_delivery_report,specific_sms_delivery_report,periodic_sms_delivery_report - Contacts:
add_contact,update_contact,delete_contact,get_contact_details,get_contact_list,get_group_contacts - Groups:
add_group,update_group,delete_group,get_group_details,get_group_list - Templates:
get_template_list,get_message_template,add_message_template,update_message_template,delete_message_template - Utilities:
register_sender_id,check_sender_id,check_sms_balance - Helpers:
get_context_snapshot,resolve_group_name
Validation & guardrails
messagelength ≤ 460;sender_idlength ≤ 11.schedule=truerequiresschedule_time(YYYY-MM-DD HH:MM).- Optional:
verify_sender=trueperforms a best‑effort sender status check before sending.
Security
- Never pass secrets as tool arguments. The server reads
MNOTIFY_API_KEYfrom the environment. - The server does not log secrets.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.