How do I install mcp-radar?

mcp-radar is a local plugin. Install it using the provided package and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is mcp-radar safe to use?

Yes. mcp-radar passed MCP Marketplace's automated security scan with a score of 10/10 (low risk). Every server on MCP Marketplace is security-scanned before it's listed; see the full security report on this page for the findings and permissions.

What AI apps work with mcp-radar?

mcp-radar uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

mcp-radar MCP Server

by th yang

Developer ToolsLow Risk10.0LocalNew

Free

Quality-ranked search across 20K+ MCP servers — skip the 98% nobody installs

About

MCP Server quality radar: score, audit and rank 20,000 MCP servers by security, activity and token cost, so you never install a dead server again

Security Report

10.0

Low Risk10.0Low Risk

Valid MCP server (2 strong, 4 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.

4 files analyzed · No issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "mcp-radar": {
      "args": [
        "-y",
        "github:XiaoMoDern/mcp-radar"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

MCP Radar 🛰️

MCP Server quality radar — find the trustworthy MCP server out of 20,000+, and avoid the 98% that nobody ever installs.

Dataset: 19,947 approved MCP servers (scraped from mcp-marketplace.io, 2026-08-25) The problem: 98% of servers have zero installs, 91% pile into "Developer Tools", only 0.1% are paid, and a single server's schema can burn 47K tokens before you even ask a question.

What it does

Works inside any MCP client (Claude Desktop / Cursor / Claude Code / etc.):

search_servers — search high-quality servers by keyword/category, ranked by an open quality score
audit_server — audit any single server before you install: 5-dimension score breakdown, installs, stars, security level, links

Scoring model (out of 100, open & reproducible)

Dimension	Weight	Meaning
Heat	25%	log-normalized install count
Security	25%	marketplace security_score
Quality	25%	avg rating + creator reputation grade
Activity	15%	recency of last update (decay)
Official	10%	official/featured bonus (marketplace self-owned excluded to avoid bias)

Quick start

pip install -r requirements.txt    # installs the MCP SDK (mcp>=1.2,<2)
python mcp_radar_server.py --stats # print dataset stats
python mcp_radar_server.py         # run as a stdio MCP server

Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "mcp-radar": {
      "command": "python",
      "args": ["/absolute/path/mcp_radar_server.py"],
      "env": { "PYTHONUNBUFFERED": "1" }
    }
  }
}

Structure

mcp-radar/
├── mcp_radar_server.py    # MCP server (official MCP SDK / FastMCP)
├── requirements.txt       # mcp>=1.2.0,<2
├── README.md
└── data/
    └── mcp_radar_data.csv # 19,947 scored servers