Notifly MCP Server
Notifly MCP Server - enabling AI agents to provide real-time, trusted Notifly documentation and SDK code examples for seamless integrations.
Notifly MCP Server
Notifly MCP Server enables AI agents to deliver real‑time, trustworthy Notifly documentation and SDK code examples for seamless integrations right inside any MCP‑compatible client.
Implements the Model Context Protocol (MCP), an open standard for enabling LLMs to interact with external tools and data.
Key capabilities:
- Documentation Search — Search Notifly docs (user guides, API reference, troubleshooting, best practices) with semantic ranking.
- SDK Search — Explore Notifly SDKs (iOS, Android, Flutter, React Native, JavaScript), Google Tag Manager templates, and implementation examples. Find symbols and retrieve production‑ready snippets.
Installation
Prerequisites
- Node.js >= 18
Quick Start
Install Notifly MCP Server:
npm i -g notifly-mcp-server@latest
Create or update the .mcp.json at your project root (or the configuration
location your MCP client uses). Using npx ensures you always run the latest
published version:
Shared MCP configuration
Add Notifly with:
{
"mcpServers": {
"notifly-mcp-server": {
"command": "npx",
"args": ["-y", "notifly-mcp-server@latest"]
}
}
}
Place this in your client’s MCP config (e.g., VS Code extension settings,
~/.cursor/mcp.json, or your Copilot client’s MCP settings).
Claude Code Configuration
Open your terminal to access the Claude Code CLI. Run the following command to register the Notifly MCP Server.
claude mcp add --transport stdio notifly-mcp-server -- npx -y notifly-mcp-server@latest
Codex Configuration
Open ~/.codex/config.toml. Add the following configuration and restart the
Codex CLI:
[mcp_servers]
[mcp_servers.notifly]
command = "npx"
args = ["-y", "notifly-mcp-server@latest"]
Restart your MCP client to load the configuration.
Command-Line Options
notifly-mcp-server [options]
--version, -v Show version
--help, -h Show help
Usage
This package runs as an MCP server. Once configured in your MCP client, you can
invoke search_docs and search_sdk directly from the client’s tool palette or
assistant UI.
Notes:
- Network access is required to fetch documentation pages and SDK source files.
- Default timeouts and result counts can be tuned via environment variables:
DOCS_SEARCH_MAX_RESULTS(default: 3)SDK_SEARCH_MAX_RESULTS(default: 3)
Local Development
Local Setup
# Clone and install
git clone https://github.com/notifly-tech/notifly-mcp-server.git
cd notifly-mcp-server
npm install
# Build
npm run build
# Run tests
npm test
# Development mode (watch for changes)
npm run dev
MCP Client Configuration for Local Development
Before the package is published, configure your MCP client to use the local build:
{
"mcpServers": {
"notifly": {
"command": "node",
"args": ["/absolute/path/to/notifly-mcp-server/dist/index.js"]
}
}
}
Replace /absolute/path/to/notifly-mcp-server with your actual project path.
Contributing
Contributions are welcome! Please read our guidelines in CONTRIBUTING.md and open an issue to discuss significant changes before submitting a PR.
Support
If you encounter issues or have feature requests, please open an issue on GitHub. For usage questions, check the docs and examples returned by the tools.
License
MIT License with Custom Restrictions - see LICENSE for details.
Resources
関連サーバー
Scout Monitoring MCP
スポンサーPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Figma MCP Server
Enables AI assistants to interact with Figma via WebSocket for reading data and design analysis.
mcpcodeserver
Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.
Code Summarizer
A command-line tool that summarizes code files in a directory using Gemini Flash 2.0.
Modellix Docs
Search the Modellix knowledge base to quickly find relevant technical information, code examples, and API references. Retrieve implementation details and official guides to solve development queries efficiently. Access direct links to documentation for deeper context on specific features and tools.
Background Process MCP
A server that provides background process management capabilities, enabling LLMs to start, stop, and monitor long-running command-line processes.
Model Context Protocol servers
A collection of reference implementations for the Model Context Protocol (MCP), showcasing servers implemented with TypeScript and Python SDKs.
Ollama MCP Bridge
A bridge API service connecting Ollama with Model Context Protocol (MCP) servers.
MCP Agentic AI Crash Course with Python
A comprehensive crash course on the Model Context Protocol (MCP), covering everything from basic concepts to building production-ready MCP servers and clients in Python.
Multichain MCP Server
A toolkit for building and deploying AI agents with blockchain capabilities, featuring a Model Context Protocol (MCP) server.
MCP Memory Gateway (rlhf-feedback-loop)
Local-first RLHF feedback loop for AI agents — capture preference signals, promote memories, block repeated mistakes, export DPO/KTO training pairs