Query trust scores for MCP servers and agent skills. Check if a tool is safe before using it.
Vigile scans and scores MCP servers and agent skills for security issues like tool poisoning, data exfiltration, prompt injection, and supply chain attacks. This MCP server brings those trust scores into your AI workflow — so your coding assistant can check whether a tool is safe before using it.
5 tools: look up server trust scores, check agent skills, scan raw file content, search the trust registry, and assess location-related privacy risks. Covers servers from npm, Smithery, PyPI, MCP Marketplace, and other registries, plus agent skills from Claude Code, Cursor, and OpenClaw.
Set these up before or after installing:
Environment variable: VIGILE_API_KEY
Sign up freeOnce installed, try these example prompts and explore these capabilities:
Add this to your MCP configuration file:
{
"mcpServers": {
"vigile-mcp-server-launch-guide": {
"args": [
"-y",
"vigile-mcp"
],
"command": "npx"
}
}
}Valid MCP server (2 strong, 4 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry. Trust signals: trusted author (2/3 approved).
Scanned 9 files · 1 finding
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Be the first to review this server!