agent-plugins — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 clay-run · MCP Server · ★ 119

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

🔒 Is agent-plugins safe to install? View the security audit →

About agent-plugins

Build with Clay in your AI coding agent — skills, MCP tools, and the clay CLI, for Claude Code, Codex, and Cursor. Docs · Getting started Clay is a go-to-market data and automation platform — search for companies and people, run enrichment routines, and query tables, all from natural language. This repo is the plugin marketplace for : one plugin source, three coding-agent targets, sharing one set of skills and one CLI. Example No Clay UI, no manual list-building — your agent chains two Searches into a Clay-managed function on its own. Set up New here? P

ai-agentsclaude-codeclayclicodexcursordata-enrichmentgo-to-marketmcp

Quick Facts

Stars119
Forks21
LanguageShell
CategoryMCP Server
Quality Score64.4910772146906/100
Open Issues13
Last Updated2026-09-18
Created2026-06-17
Platformsclaude-code, cli, codex, mcp
Est. Tokens~11k

Compatible Skills

These tools work well together with agent-plugins for enhanced workflows:

  • devin-handoff — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • bdpan-storage — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)

agent-plugins alternative? Top 6 similar tools

Looking for a agent-plugins alternative? If you're comparing agent-plugins with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agnix by agent-sh · ⭐ 421

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • ai-skills by sanjay3290 · ⭐ 422

    24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T

  • Context-Engine by Context-Engine-AI · ⭐ 402

    Context-Engine MCP - Agentic Context Compression Suite

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • google-ai-mode-mcp by PleasePrompto · ⭐ 151

    MCP server for free Google AI Mode search with citations. Query optimization, CAPTCHA handling, multi-agent su

  • agent-designer by appautomaton · ⭐ 130

    Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is agent-plugins?

agent-plugins is Build with Clay in your AI coding agent - skills, MCP tools, and the clay CLI for Claude Code, Codex, and Cursor. Search companies and people, run enrichment routines, and query tables from natural la. It is categorized as a MCP Server with 119 GitHub stars.

What programming language is agent-plugins written in?

agent-plugins is primarily written in Shell. It covers topics such as ai-agents, claude-code, clay.

How do I install or use agent-plugins?

You can find installation instructions and usage details in the agent-plugins GitHub repository at github.com/clay-run/agent-plugins. The project has 119 stars and 21 forks, indicating an active community.

What are the best alternatives to agent-plugins?

The top alternatives to agent-plugins on Agent Skills Hub include agnix, ai-skills, Context-Engine. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

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