MCP servers and skills: search, filter by where they run, and compare.
Official MCP server support for TestRelic AI - Build, Plan, Debug, Analyze with AI native intelligence
Node.jsAGPL-3.0★ 4Few starsNo key
BrowserStack's Official MCP Server
OfficialNode.jsAGPL-3.0★ 155No key
Executed-evidence verification gate for AI coding agents
PythonAGPL-3.0★ 4Few starsNo key
Open-source adaptive A/B testing where the whole test lives in a URL: no accounts, no API keys, one joint Thompson-sampling model. Built to be driven by AI agents as much as by people.
Node.jsAGPL-3.0★ 2Few starsNo key
Node.jsAGPL-3.0★ 4Few starsNo key
Hosted by authorAGPL-3.0Few starsNo key
Let AI agents test your Android apps. No test scripts — just natural language. Open source MCP server.
SkillAGPL-3.0★ 4Few starsNo key
Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.
SkillAGPL-3.0★ 46No key
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-V
SkillAGPL-3.0★ 10No key
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
PythonAGPL-3.0★ 7.8kNo key
Persistent cross-session memory for AI coding assistants. Works with Claude Code, Cursor, Windsurf, Cline, OpenClaude, and MCP-compatible editors.
Node.jsAGPL-3.0★ 11No key
Node.jsAGPL-3.0Few starsNo key
AI-powered E2E testing Agent Skill — self-healing DevQA loop for Claude Code, Codex, Cursor, and 11+ AI coding tools
PythonAGPL-3.0★ 1Few starsNo key
Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)
SkillAGPL-3.0★ 2.8kNo key
Security MCP server that turns your AI into a penetration tester. 20 tools, 100 best practice guides, 47 vulnerability patterns. Connect to Claude, Cursor, or any MCP client.
SkillAGPL-3.0★ 4Few starsNo key
An open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间，让人与智能体在此协作
SkillAGPL-3.0★ 47kNo key
The Universal 245K Agent Microkernel for Local LLMs.
Node.jsAGPL-3.0★ 10No key
🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.
SkillAGPL-3.0★ 436No key
Self-hosted gym & body-weight tracker — plan routines, log workouts (supersets, warm-ups, cardio), see which muscles are trained, fatigued or detrained, import from FitNotes/Strong/Hevy, passkey login
SkillAGPL-3.0★ 13kNo key
Kibi is a requirement-conformance layer for AI coding agents that keeps product intent connected to code and tests, and catches when implementations drift from it.
SkillAGPL-3.0★ 10No key
Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a
PythonAGPL-3.0★ 4Few starsNo key
Hosted by authorAGPL-3.0★ 1Few starsNo key
Self-hosted, secure tunnel server in Rust. Expose local HTTP/HTTPS/TCP/UDP services to the public internet via TLS-encrypted WebSocket. Open-source, pay-as-you-go managed option, MCP server for AI age
SkillAGPL-3.0★ 658No key
Who stands behind it
