MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Framework-agnostic live WebRTC inspection and fault injection: peer connections, tracks, data channels, WebSockets, fake mic/camera, and real transport/signaling fault injection for reconnect testing.
npm MIT -
Security auditor for AI agents and MCP servers — config analysis, prompt injection testing, tool probing, data flow tracing
npm MIT -
MCP server interface for AI agent and MCP security auditing — config analysis, trust audits, prompt injection testing, tool probing, and data flow tracing
npm MIT -
HTTP and HTTPS fault-injection proxy for development and testing: see every outbound call your app makes, then slow it down, fail it or cut it off on purpose
MIT ★ 1 -
Fable 5.1 Multi-Agent Architect & Invariant Verification Gate for Claude Code, Cursor & Web. Decouples task contracts from worker subagents with adversarial failure injection testing. BYOK (Claude 3.7, GPT-4o, DeepSeek, Ollama).
MIT ★ 1 -
Stealth browser automation for AI agents — unattended, headless, N parallel persistent logged-in Chromes. One MCP server + CLI, credential vault with TOTP/IMAP 2FA, vision clicking, prompt-injection scanning. Self-hosted, real Chrome. 2,027 tests.
Apache-2.0 ★ 9 -
55-tool MCP server for security scanning of MCP servers. Runtime inspection, AST-based SAST, config audit, dependency analysis, OWASP MCP Top 10 compliance. OAuth, TLS, fuzz testing, prompt injection, tool mutation detection. 100% local, zero external API calls.
MIT ★ 5 -
AIContextBuilder (AICB): semantic code intelligence for AI coding agents on C#/.NET (dotnet). Roslyn MCP server and CLI: change impact, static analysis, code navigation (callers, implementations, dependency injection, tests, side effects, dead code) and context engineering. For Claude Code, Codex, OpenCode, Cursor; Windows desktop app included.
NOASSERTION ★ 12 -
Fork failed Python programs into tested alternate outcomes, with original-run controls and guarded replay.
NOASSERTION -
mcp-chaos-riggithub.com/typewise/mcp-chaos-rigupdated this year
A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry.
npm MIT -
hackbrowser-mcpgithub.com/badchars/hackbrowser-mcpupdated this year
The first browser MCP built for security testing. Give your AI agent a real Firefox browser and let it find vulnerabilities.
MIT ★ 24 -
Replay the crash. Prove the fix. 81ns in-process flight recorder, 61µs deterministic replay, and 5.9ms variant fix verification for journal-driven services and AI coding agents.
Apache-2.0 ★ 2 -
MCP server for live Qt UI automation. Inject into running QWidget or QML/QQuickWindow apps, query the live tree, act/get/set/call, screenshot/annotate, and resolve QML source. Qt 5/6; Windows/Linux.
pypi MIT ★ 9 -
Test the protocols your show, installation or IoT gear speaks: send, capture, emulate and impair OSC, UDP/TCP, HTTP, WebSocket and MQTT — by hand, as repeatable experiments and load tests, or from the CLI, CI and MCP. Windows, Linux, server and Docker.
MIT ★ 14 -
Debug and fault-test any WebRTC session — Chrome extension, MCP server for AI coding agents, npm library, and Playwright plugin. Live RTCPeerConnection/WebSocket inspection, reconnect testing, network-loss simulation.
MIT ★ 4 -
mcp-guardiangithub.com/aryan877/mcp-guardianupdated this year
An MCP server that scans, tests, and locks down other MCP servers. Built on Archestra.
MIT -
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.
pypi AGPL-3.0 ★ 21 -
The crash test for AI coding agents: 19 realistic traps for Claude Code, Codex and Gemini CLI in a sealed container, plus a safety grade with fix prompts for apps built with Lovable, Bolt, v0 and Replit.
Apache-2.0 ★ 1 -
MCPGoatgithub.com/SabyasachiDhal/MCPGoatupdated this year
Deliberately vulnerable MCP server (aka MCP Goat) for security training — 26 challenges across 4 difficulty levels (incl. a secure reference), a victim-agent harness, and one-command Docker deploy. Practice penetration testing against the Model Context Protocol.
MIT ★ 12