MCP Playground & Security Scanner

Free online MCP (Model Context Protocol) playground. Test endpoints with JSON-RPC requests and run a security scanner. All 100% client-side.

Features

• JSON-RPC request testing against MCP servers
• Tool and resource discovery (tools/list, resources/list)
• 30-point MCP security scanner
• CORS and authentication checks
• Schema inspection for tool arguments
• 100% client-side

Frequently Asked Questions

What is the Model Context Protocol (MCP)?

MCP is an open protocol (introduced by Anthropic) that standardizes how AI assistants connect to external tools and data sources. It uses JSON-RPC 2.0 over stdio or HTTP, letting models call tools, read resources, and receive prompts from any MCP-compatible server.

What does the MCP security scanner check?

It inspects an MCP server for common risks including dangerous tool names, missing input validation, prompt-injection-prone descriptions, missing authentication, permissive CORS, and overly broad capabilities.

Are MCP requests sent through a server?

Requests go directly from your browser to the MCP endpoint you specify. The playground itself runs client-side and does not proxy your traffic.