MCP Servers
64,188 MCP servers for AI apps. Filter by category, badge and popularity.
Developer Tools
Provision, SSH into, run commands on, and manage Linux VPSes from an AI agent. Pay USDC over x402 (Base) or by card over HTTP 402, with a running box in under 60 seconds. No signup, no API key to buy. Includes get_catalog, provision_server, get_server, list_servers, extend_server
MCP Hub tool allows searching MCP tool lists by keyword via `search_mcp`, and viewing detailed descriptions (such as features and installation steps) via `get_mcp_detail`. Users can quickly locate required tools and obtain deployment guides, such as Python's `pip install` or Docker integration methods, improving development efficiency. Data is based on the MCP Hub database, supporting precise filtering and metadata retrieval
The MCP server that vets MCP servers. Connect your agent to the PolicyLayer registry and check any MCP server's identity, risk grade, auth posture and tool classifications before installing it. Free single-server lookups over 32,500+ published servers and 515,000+ classified tools
A standardized security evaluation framework for MCP servers, including assessment templates and an automated vulnerability scanner. This registry helps developers identify secure implementations for AI applications and promotes best practices across the MCP ecosystem.
Scan any GitHub repository for 21 AI/ML vulnerability patterns across Python, Java, Go, C++, and Rust. Detects eval injection, pickle deserialization, SSRF, command injection, SQL injection, unsafe YAML, hardcoded secrets, and more. Severity-weighted risk scoring with line-level
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
