mcp-servers — security grade SAFE, quality 40/100

Security audit verdict: SAFE · quality 40/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by cursor · MCP Server · ★ 226

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is mcp-servers safe to install? View the security audit →

About mcp-servers

MCP Servers This repository is deprecated. Use cursor.directory instead. New plugins can be submitted at cursor.directory/plugins/new.

Quick Facts

Stars226
Forks95
CategoryMCP Server
Quality Score39.6989685116355/100
Last Updated2026-03-19
Created2025-08-30
Platformsmcp
Est. Tokens~23k

Compatible Skills

These tools work well together with mcp-servers for enhanced workflows:

  • servers — semantic(0.57)+complementary+same_lang+shared_platform (55%)
  • mcp — semantic(0.32)+same_lang+similar_pop+shared_platform (46%)
  • airtable-mcp-server — semantic(0.31)+same_lang+similar_pop+shared_platform (46%)
  • typescript-sdk — semantic(0.30)+complementary+same_lang+shared_platform (46%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Frequently Asked Questions

What is mcp-servers?

mcp-servers is A list of MCP (Model Context Protocol) servers for developer tools and services. It is categorized as a MCP Server with 226 GitHub stars.

How do I install or use mcp-servers?

You can find installation instructions and usage details in the mcp-servers GitHub repository at github.com/cursor/mcp-servers. The project has 226 stars and 95 forks, indicating an active community.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools