Mention MCP Server
Monitor web and social media using the Mention API.
Mention MCP Server
A production-ready Model Context Protocol (MCP) server for social listening and monitoring through the Mention API. Built with TypeScript, comprehensive error handling, structured logging, and modular architecture.
Supported Tools
| Tool | Description |
|---|---|
get_account_info | Retrieve account details and subscription plan |
get_app_data | Get available languages, countries, sources |
list_alerts | List all monitoring alerts with pagination |
get_alert | Get detailed information about specific alerts |
create_basic_alert | Create alerts with simple keyword matching |
create_advanced_alert | Create alerts with boolean query syntax |
update_alert | Modify existing alert criteria and settings |
pause_alert | Temporarily pause monitoring for specific alerts |
unpause_alert | Resume monitoring for paused alerts |
fetch_mentions | Retrieve mentions with advanced filtering |
fetch_alert_stats | Get comprehensive statistics for alerts |
Installation & Usage
Quick Start with Claude Desktop
Add the following to your Claude Desktop configuration file:
{
"mcpServers": {
"mention": {
"command": "npx",
"args": ["-y", "@maelitop/mention-mcp-server"],
"env": {
"MCP_MENTION_API_KEY": "your_mention_api_key_here"
}
}
}
}
Environment Variables
| Variable | Description | Default |
|---|---|---|
MCP_MENTION_API_KEY | Your Mention API key (required) | - |
MCP_MENTION_API_BASE_URL | Custom API base URL | https://web.mention.com/api |
MCP_LOG_LEVEL | Logging level (debug, info, warn, error) | info |
MCP_CONSOLE_LOGGING | Enable console logging (true/false) | false |
MCP_REQUEST_TIMEOUT | Request timeout in milliseconds | 30000 |
MCP_MAX_RETRIES | Maximum retry attempts | 3 |
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Run tests
npm test
# Build for production
npm run build
# Run linting and type checking
npm run ci
Logging
Logs are automatically written to platform-specific directories:
- macOS:
~/Library/Logs/mention-mcp-server/mention-mcp-server.log - Windows:
~/AppData/Local/mention-mcp-server/logs/mention-mcp-server.log - Linux:
~/.local/share/mention-mcp-server/logs/mention-mcp-server.log
Testing
# Run all tests
npm test
# Run tests with coverage
npm run test:coverage
# Run tests in watch mode
npm run test -- --watch
License
This project is licensed under the MIT License.
เซิร์ฟเวอร์ที่เกี่ยวข้อง
Bright Data
ผู้สนับสนุนDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Canvas LMS
Links AI tools to Canvas school dashboards.
Configurable Puppeteer MCP Server
A configurable MCP server for browser automation using Puppeteer.
Read URL MCP
Extracts web content from a URL and converts it to clean Markdown format.
MCP Webscan Server
Fetch, analyze, and extract information from web pages.
Web Scraper Service
A Python-based MCP server for headless web scraping. It extracts the main text content from web pages and outputs it as Markdown, text, or HTML.
Webclaw
Web content extraction for LLM pipelines — clean markdown or structured JSON from any URL using browser-grade TLS fingerprinting, no headless browser required. CLI, REST API, and MCP server.
Novada-MCP
Search, extract, crawl, map, and research the web — from any AI agent or terminal.
Influship Influencer Marketing MCP
AI Influencer Search, Creator Data, & Live Scraping
Scrapezy
Turn websites into datasets with Scrapezy
Driflyte
The Driflyte MCP Server exposes tools that allow AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages.