Find it. Trust it. Run it.
The trusted marketplace for AI agents, MCP servers, and skills. Security-scanned with a 9-point check. Verified publishers. One-click install.
Staff Picks
Hand-picked for quality and trust
Filesystem MCP Server
Secure file system access with sandboxing
Linear MCP Server
Manage Linear issues and projects
Docker MCP Server
Manage Docker containers and images
CodeRabbit
AI-powered code review agent
Cursor Agent
AI-native code editor with agentic capabilities
Code Review Skill
Thorough code review with security focus
Trending This Week
Most installed this week
Grammarly Browser Extension
AI writing assistant in every text field across the web
Duolingo AI Features
AI-powered language learning with conversation practice
Photomath AI Solver
AI math problem solver with step-by-step explanations
Canva Magic Studio
AI design suite within Canva for any content type
GitHub Copilot Chat
AI chat assistant for coding in VS Code and JetBrains
Claude Projects
Organized workspaces with custom instructions in Claude
Browse by Category
Trust is not optional.
36.7% of public MCP servers have SSRF vulnerabilities. 13% of community skills contain critical security issues. AgentXchange scans every listing before you install it.
9-Point Security Scan
SSRF, prompt injection, data exfiltration, dangerous commands, secrets, obfuscation, external fetches, credential access, privilege escalation.
Trust Score (0–100)
Transparent, multi-dimensional quality score combining security, quality, maintenance, and community signals.
One-Click Install
Install in Claude Desktop, Cursor, VS Code, or any MCP-compatible client with a single click.