TrendRadar
A self-hosted trend and news monitor with an MCP server: hot-topic aggregation, RSS and smart alerts
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- The service reaches the network and collects data from external platforms
- It sends alerts to external channels per your configuration
Install
Manual install
docker compose up -d trendradar-mcpStarts the MCP service within docker compose; the main trendradar service is started separately.
This is third-party code. Review the repository files before installing.
What it does
TrendRadar collects hot topics from many platforms and RSS feeds, filters them by keywords and pushes digests to messengers and email. A separate MCP server exposes this data to an agent: you can chat about trends, analyze sentiment and reason about momentum in natural language. It installs through uv or Docker and keeps data locally or in the cloud as you choose. The MCP server listens on a local port and connects to clients such as Claude Desktop or Cline.
Who it is for. For marketers, SMM and analysts who need news monitoring with agent-driven analysis.
Good fit when
- You need to track hot topics by keyword and get digests
- You want to discuss trends and sentiment with an agent over MCP
- You need alerts about spikes of interest in messengers
Not a fit when
- You want a turnkey cloud service with no self-hosting
- You only care about platforms outside the supported sources
Example request
Show today's hot topics for my keywords and assess their sentimentLimitations
You self-host the service through uv or Docker. The MCP server listens only on 127.0.0.1 by default; remote access needs a reverse proxy and authentication you set up. The main hot-topic sources are oriented toward Chinese platforms.
How to disable. Stop the trendradar-mcp container (docker compose stop trendradar-mcp) and remove the trendradar entry from your client's MCP config.
MCP
- Transport
- http
- Authentication
- not required
Security check
- The service reaches the network and collects data from external platforms
- It sends alerts to external channels per your configuration
README in short
The README describes TrendRadar as an aggregator of hot topics across several platforms and RSS, with keyword filtering and smart alerts to popular channels. It highlights an MCP server that gives an agent conversational access to the data for sentiment and trend analysis. Installation is available through uv, Docker and docker compose, including a separate trendradar-mcp image. GPL-3.0 licensed.
FAQ
Is MCP required?
No, TrendRadar also works as a plain monitor with alerts. MCP adds agent-driven trend analysis.
Where do alerts go?
To WeChat, Feishu, DingTalk, Telegram, Slack, email and via ntfy or bark, per your configuration.
Related
A skill that strips AI writing tells from text using Wikipedia's list, without adding invented facts
Marketing Skills for AI agents
Marketing Skills for AI Agents
About fifty skills for CRO, copywriting, SEO, analytics, ads and launches, built for coding agents
SendPulse MCP server
SendPulse MCP
SendPulse's official remote MCP server: statistics, campaigns and user data through an agent chat
Yandex Direct MCP generated from a machine-readable schema
yandex-direct-mcp
An MCP server and CLI covering all 113 Yandex Direct API v5 methods generated from WSDL, exposing 9 read tools by default and writes only on demand