"Damn Vulnerable MCP" matching MCP servers:

Damn Vulnerable MCP Server for Security Researchers.

A local MCP server to control iClone 8's visible interface like a human user, providing read-only inspection and screen capture tools.

Enables AI agents to interact with, test, click buttons on, and verify Telegram bots end-to-end via MTProto, including messaging, inline queries, media exchange, and automated test suites.

Enables generating Robot Framework test cases with SeleniumLibrary, creating page object models, and performing performance monitoring through natural language.

Enables interacting with, testing, and automating Telegram bots directly from a terminal, using MTProto and Telethon session files to send messages, trigger commands, click inline buttons, fetch history, upload files, and run arbitrary MTProto snippets.

Enables reading, validating, and managing Minecraft resource packs, including structure checks, asset listing, pack comparison, and Modrinth queries.

Automatically detects security vulnerabilities in AI-generated code, scanning for hardcoded secrets, injection flaws, XSS, weak cryptography, authentication issues, path traversal, and vulnerable dependencies across JavaScript, Python, Java, and Go.

Unity Editor adapter for the DCC MCP ecosystem, providing tools to inspect and modify Unity projects, scenes, builds, and diagnostics through a WebSocket bridge.

Enables AI clients to validate game level progression data, audit localization packs for missing translations and dynamic-token mismatches, and run deterministic evaluations of generated puzzle or notification content.

A vulnerable-by-design MCP server pair (NotesServer and VaultServer) for testing MCP security tools, featuring confused-deputy, prompt injection, and authorization bypass scenarios.

A comprehensive testing suite demonstrating all Model Context Protocol (MCP) Apps features through interactive Weather Dashboard and 3D Globe viewer applications.

Demonstrates an MCP server with a vulnerable add tool protected by SonnyLabs prompt injection detection.

A TypeScript MCP server for TypeSafe Jev, exposing one tool for batched classification, rubric scoring, and yes/no judgments with probabilities and token usage. Includes Codex compatibility checks and requires a TypeSafe API key.

Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.

Enables agents to inspect web pages for Cloudflare Turnstile challenges without an API key, and clear Turnstile or WAF challenges using a SolveGate API key.

A remote MCP server exposing 3 tools via Model Context Protocol: score_prompt (free, grades any LLM prompt A-F on 0-40 scale), optimize_prompt (returns optimized prompt + dimension breakdown, $0.025 USDC), and compare_models (Claude vs GPT-4o head-to-head, $1.25 USDC). Remote HTTP server at /api/mcp.

An MCP server that diagnoses Flutter + Stripe (flutter_stripe) setup issues — so Claude can check your project automatically.

Browser automation that bypasses anti-bot systems and handles web-scraping with CDP Mode.

Enables MCP clients like Claude Desktop and Claude Code to drive a real browser with SeleniumBase automation. Offers three variants: WebDriver-based general automation, Pure CDP Mode for bot-detection bypass, and a broad SB() API with MFA and downloads.

Free VOP (Verified Output Protocol) verification for AI agent outputs — score any output 0-100 and get a PASS/PARTIAL/FAIL verdict. No account, no escrow, no financial transaction of any kind.