MCP servers and skills: search, filter by where they run, and compare.
MockServer is an HTTP(S) mock server and proxy for testing that lets you mock APIs, inspect and modify live traffic, and inject failures. It supports HTTP/1.1, HTTP/2, gRPC, WebSockets, TCP and more o
DockerApache-2.0★ 5.0kNo key
🤖 Aurora QA — AI-powered autonomous quality engineering platform. Multi-agent pipelines, self-healing tests, chaos engineering, MCP server & real-time dashboard.
SkillMIT★ 1Few starsNo key
AI-powered security scanner & chaos engineering platform. Multi-tier vulnerability detection, RAG-powered code analysis, auto-fix generation, and chaos simulation — all running locally with Ollama.
SkillMIT★ 1Few starsNo key
50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.
SkillMIT★ 198No key
Intensity slider from tipsy (0.1) to blackout (1.0). 5 moods, 8 creative techniques. Lowers inhibition, not intelligence. Unfiltered genius for Claude Code.
SkillMIT★ 203No key
A sandbox for the third-party APIs you depend on. Built from the provider's spec, it fails on purpose, and it replays the exact failure production hit.
GoApache-2.0★ 82No key
Fault injection toolkit for agent systems. Inject latency spikes, partial failures, 429s, malformed tool outputs, and stale context between agents and their tools. Scenario-driven. Prove your circuit
SkillMIT★ 2Few starsNo key
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
SkillMIT★ 14No key
Injects realistic failures into AI agents — broken connectors, expired auth, prompt injection, schema drift, truncated payloads — and judges from tool-boundary evidence whether the agent reported the
SkillMIT★ 1Few starsNo key
107 production-grade QA engineering skills for AI agents — frontend, API, performance, mobile, security, CI, and AI/LLM testing. MCP-ready: works with Claude Code, Claude Desktop, Cursor, Zed, Windsur
SkillMIT★ 5No key
Verification-first AI-assisted development harness. 5 layers from spec to pentest.
SkillMIT★ 10No key
Standardized Claude Code bootstrap — drop-in .claude/ tree with a 19-agent adversarial review team, Ralph Loop, dev-flow skills, and an init script. Agnostic, project-ready.
SkillMIT★ 6No key
Deterministic fault injection and autonomous resilience tests for DeepSeek Harness tools
SkillMIT★ 4Few starsNo key
Test how MCP clients handle failures and recover. Run repeatable scenarios against built-in faults or external MCP servers.
Node.jsMIT★ 4Few starsNo key
Prove your AI agent fails safely. Fault injection for LLM, RAG, and tool-call failures: declare what must never happen, find the silent failures, and keep the proof on every pull request.
SkillApache-2.0★ 3Few starsNo key
Property-based reliability testing for tool-using AI agents under partial failures.
PythonApache-2.0★ 1Few starsNo key
Chaos testing for AI agents. Break the MCP tools your agent depends on, score how it copes, fix what broke. Claude Code plugin + GitHub Action.
GoMITFew starsNo key
OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.
PythonMIT★ 2Few starsNo key
Fault injection and reliability scoring for MCP servers
PythonApache-2.0★ 1Few starsNo key
Load and chaos testing for AI agent orchestration plumbing: adversarial mock model endpoint + mock MCP tool fabric, knee detection with CIs, honest confidence labels.
PythonApache-2.0★ 1Few starsNo key
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
GoMIT★ 1Few starsNo key
Agent Skill for chaos-TDD on LLM agent pipelines: deterministic fault injection at seams that already exist, where the fault-injection test is written first as the specification and the guard ships in
SkillMITFew starsNo key
A local test harness for AI agent systems. Compare the same work before and after a change.
SkillApache-2.0Few starsNo key
A production-grade AIOps framework focused on model integrity and autonomous reliability. Features a LightGBM-driven multiclass inference engine via FastMCP, validated against data leakage through NMI
SkillMIT★ 2Few starsNo key
Who stands behind it
