Explore

🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration...

Skill·Apache-2.0·★ 314·No key

SDK monorepo for the Ethora chat / messaging platform. (1) Pick an SDK for your frontend stack. (2) Integrate manually or with ethora-setup. (3) Optionally configure app settings, deploy AI agents etc

in the readmeweb app (React.js) — App Builder frontend | Active | | `playground/` | ethora-sdk-playground | SDK testing & demo playground | Active | | `backend-integration/` | ethora-sdk-backend-integration | Backend integration examples | Active

Skill·Apache-2.0·★ 550·No key

An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.

Skill·MIT·★ 1.8k·No key

👨‍💻 Instructions, prompts, and chat modes to help You with test automation for GitHub Copilot 🤖

in the readmehelp testers, developers, and quality engineers leverage AI to improve their testing practices, automate repetitive tasks, and enhance the overall quality of software products. > [!TIP] > 💡 Choose

Skill·MIT·★ 116·No key

MCP to Capture HTTP requests, emails, and DNS lookups test webhooks, debugg API callbacks

in the readmefor webhook.site - instantly capture HTTP requests, emails, and DNS lookups. Perfect for testing webhooks, debugging API callbacks, security testing, and bug bounty hunting. Security helper tools

Python·MIT·★ 13·No key

Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

MCP·Link only·★ 2.3k

Open Source Generic MCP Client for testing & evaluating mcp servers and agents

Node.js·MIT·★ 137·No key

Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.

in the readmesuper app for real work** — CoWork OS keeps coding, email, research, browser testing, documents, spreadsheets, presentations, PDFs, channels, devices, automations, memory, providers, and approvals in one

Node.js·MIT·★ 484·No key

Han: AI skills and agents for "Solo" product engineers and small teams

in the skill textspecialist agents, such as project managers, adversarial reviewers, investigators, architectural analysts, and testing and security specialists, to do the judgment-heavy work. It then folds their

Skill·MIT·★ 289·No key

One command installs 670+ security tools on Debian/Ubuntu/Kali, Fedora, Arch, openSUSE and Termux. Its authorization-gated MCP server runs them in a disposable Kata Containers VM sandbox for Claude Co

in the readmeyes | yes | Offensive security | | `web` | misc, networking, recon, web, llm | — | — | Web application testing | | `osint` | misc, recon | — | — | OSINT gathering | | `forensics` | misc, forensics, blueteam, reversing, stego, cracking | — | — | Digital

Skill·MIT·★ 72·No key

Safe local execution layer for AI agent tools. Build and test-run MCP tools (no pass, no run), serve them from a built-in MCP server, and use them in Agentic Chat with RAG, human-in-the-loop approval,

in the readmeTools** Spring AI Playground is a cross-platform desktop app for building, testing, validating, and executing MCP tools in a controlled local environment. It helps you

Skill·Apache-2.0·★ 145·No key

Official one-stop shop for AI Agents and developers building with Telnyx.

in the skill textwork in progress under active development. We are continuously improving based on testing and feedback. Contributions and feedback encouraged! ## Table of contents - Telnyx Plugins - Set

Skill·MIT·★ 221·No key

⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel, Target Memory & Deterministic Automation.

in the readmeChrome Extension Manifest V3 ](    ![License Apache

Node.js·Apache-2.0·★ 13·No key

Inspectr – easily view and analyze API requests, MCP server calls and webhook events.

in the readmewith a built-in tunnel/expose option for sharing local services. Useful for testing integrations, monitoring incoming requests, reviewing past requests, or troubleshooting payload issues, Inspectr provides

Node.js·GPL-3.0·★ 13·No key

Agent Skill and repository template for end-to-end software development entirely inside ordinary Web AI chat.

in the skill textmissing pieces. ## What you get - **A useful built-in workspace.** Editing, building, testing, and debugging stay in the chat sandbox whenever it can do the job

Skill·MIT·★ 66·No key

MCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copi

in the readmeadd/modify/remove tools without touching main server - **Organization**: Tools grouped logically by functionality - **Testing**: Individual tool modules can be unit tested separately - **Reusability**: Tool modules can

Skill·MIT·★ 58·No key

Awesome QA Skills is an open-source AI-native Quality Engineering skill system that helps engineering teams reason about, design, execute, evaluate, and continuously improve software quality across th

Skill·Link only·★ 256

WhatsApp Web MCP Server

in the readmeclient integration and API-based connectivity ## Disclaimer **IMPORTANT**: This tool is for testing purposes only and should not be used in production environments. Disclaimer from WhatsApp

Node.js·MIT·★ 46·No key

This Streamlit application provides a user interface for connecting to MCP (Model Context Protocol) servers and interacting with them using different LLM providers (OpenAI, Anthropic, Google, Ollama).

in the readmesession memory - **Multi-Server Support**: Connect to multiple MCP servers simultaneously - **Tool Testing Interface**: Test individual tools with custom parameters - **Chat-Only Mode**: Use without MCP

Skill·MIT·★ 49·No key

Self-Hosted Mobile Device Streaming for QA Teams 2026

MCP·Link only·★ 115

Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.

in the skill textonly the user can supply (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). The output is a `CLAUDE.md` under

Skill·MIT·★ 63·No key

Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 136 API endpoints. Desktop app, CLI, Telegram — all connected. Rust-powered.

in the readmeYou get a full Swagger-style explorer: every endpoint documented, live request > testing, and code-snippet generation for **curl, Python, Go, TypeScript, Rust**, and more

Skill·MIT·★ 24·No key

MCP Server for a Matrix home server integration; chat, manage rooms, etc.

in the readmestart ``` ### Development Mode ```bash # Start with hot reload (OAuth disabled for easier testing) npm run dev # Or start with OAuth enabled ENABLE_OAUTH=true npm run

Skill·MIT·★ 53·No key

Personal digests from Telegram channels and chats: summarizes threads, extracts key points, and delivers a clean daily/weekly brief with links and context.

in the readmeMCP server : enabling , stdio mode , tools , single channel , searching , security - Development and testing - FAQ - Contributing · License · Credits ## Features - Reads channels in any language: English, Russian, Ukrainian

Skill·MIT·★ 23·No key

OAuth-based multi-user Slack MCP server with HTTP transport

in the readmeread.email` `search:read` 4. Add **Redirect URL** under **OAuth & Permissions**: - For local testing: Use an HTTPS proxy like ngrok (E.g: ` See local development setup below. - For

Python·Apache-2.0·★ 9·No key

MCP server for virtual phone number verification - SMS activations for AI agents via Claude, Cursor, VS Code Copilot and more...

in the readmedownloads ]( ![License: MIT ]( ![Smithery ]( Platfone provides virtual phone numbers for account verification, testing, and automation workflows. The Platfone MCP server enables AI agents to obtain temporary

Node.js·MIT·★ 4·Few stars·No key

Running Microsoft's BitNet inference framework via FastAPI, Uvicorn and Docker.

in the readmeresearchers to programmatically control `llama-cli` and `llama-server` processes for automated testing, benchmarking, and interactive chat sessions. ## Key Features * **Session Management**: Start, stop, and check

Skill·MIT·★ 42·No key

Test-suite hygiene scorecard for QA and engineering teams — findings and questions, not a verdict

Node.js·Apache-2.0·★ 4·Few stars·No key

Signal generator control for the embedded bench — CLI + MCP server for AI agents (Siglent SDG series)

in the readmevia MCP. Sibling of devpower (USB power control). Typical use: an agent testing an ADC driver or input-capture firmware needs a known stimulus — it sets

Python·MIT·★ 3·Few stars·No key

AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any

in the skill textscreenshots | Screenshots + Claude Vision | | **QA workflow** | Manual checklist | **Automated QA checklist** | | **Viewport testing** | Manual | **Device presets** (iPhone, iPad, Pixel...) | | **DOM inspection** | Via DevTools | **Built-in inspector

Skill·MIT·★ 12·No key

Chat with your SonarQube data: explore metrics, compare trends, and track issues—effortlessly.

in the readmeclient-server communication. The client included in the project is only for testing how the code works; we recommend using Claude Desktop or developing your own

Skill·Apache-2.0·★ 14·No key

Instant no-signup webhook & HTTP-request inspector for testing webhooks and agent tool-callbacks.

Hosted by author·No license·Few stars·No key

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

in the skill texthave `gcloud`, use the manual setup below instead. > [!WARNING] > **Scope limits in testing mode:** If your OAuth app is unverified (testing mode), > Google limits consent

Skill·Apache-2.0·★ 31k·No key

⚡ Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x (43 tools) & 3.0+ (45+ tools).

in the readmeQuickstart/Tutorial ### 🎯 Recommended: Docker Compose (Complete Demo Environment) **For quick evaluation and testing:** ```bash git clone cd MCP-Airflow-API # Configure your Airflow credentials cp .env.example .env

Python·MIT·★ 52·No key

✨ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.

in the readmePRDs into actionable development tasks. - Task Execution - Systematic task execution with proper testing and Git practices. ## Prompts Prompts are reusable tasks or workflow instructions that help

Skill·CC0-1.0·★ 582·No key

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for remote and chat access.

in the readmeview, and more - 🎯 **Input Simulation** - Keyboard, mouse, and UI interaction for game testing - 🔄 **Editor Control** - Trigger recompilation and asset refresh remotely - 🔒 **Security Controls** - Configure what operations

Skill·Apache-2.0·★ 107·No key

Enterprise-grade PowerShell development standards, shipped as GitHub Copilot instructions and Claude Code rules, for consistent, secure, and high-quality PowerShell code across teams and projects.

in the skill textover PowerShellGet v2, with a capability check for Windows PowerShell 5.1 fallback - **Testing Standards**: Pester 6.2 patterns — `Should-*` assertions, custom assertions via `New-ShouldAssertion`, `BeforeDiscovery` data

Skill·MIT·★ 19·No key

AI agent skills, agent teams, MCP servers, and tools that make AI coding assistants better at Swift and iOS development.

in the readmemigration, and performance. - SwiftData - @Model schemas, @Query, predicates, relationships, and migration patterns. ### Testing - Swift Testing Expert - Modern Swift Testing framework with `#expect`, `#require`, traits, tags, parameterized

Skill·CC0-1.0·★ 105·No key

KakaoTalk CLI for AI agents - read and send messages via database + UI automation

in the readmekakaocli send "지수" "안녕!" # Send to self-chat (나와의 채팅) — safe for testing kakaocli send --me _ "test message" # Stream new messages as JSON kakaocli sync --follow

Skill·MIT·★ 164·No key

Manage your entire Discord server from Claude Code, Claude Desktop, Cursor, or Windsurf via MCP. 134 admin tools across 20 categories. Interactive setup wizard included.

in the readmethe Stage channel"* - *"Bulk delete the last 50 messages in #bot-testing"* - *"Give everyone with the Member role access to #private-channel"* - *"Create a poll

Node.js·MIT·★ 34·No key

Enterprise-grade AI Agent Skills for software development, DevOps, SRE, security, and product teams. Compatible with Claude Code, Cursor, Windsurf, Gemini CLI, GitHub Copilot, and 30+ AI coding agents

in the skill textTypical Workflow | |---------|--------|-----------------|------------------| | **Software R&D Agent** | Software Dev | dev-workflow + architect + gitlab-mr + testing-strategy | Requirement -> Design -> Code -> Test -> MR -> Deploy (9-step loop) | | **SRE Agent

Skill·Apache-2.0·★ 44·No key

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

in the skill textSpec & Code Quality Reviewers (Compliance Officers) * Test-Driven Development (The Iron Law) * Testing Anti-Patterns (Lazy QA Training) * Systematic Debugging (Forensic Engineering) * Root Cause Tracing & Defense

Skill·MIT·★ 93·No key

Automated AI code reviews powered — webhook-driven, real-time dashboard, MCP integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for GitLab MRs and GitHub

in the readmereview runs a configurable set of specialized audit agents — Clean Architecture, SOLID, Testing, DDD, Code Quality, and more. Define your own agents per project to match

Node.js·MIT·★ 44·No key

Next-Generation Multi-Agent Collaboration Platform and Workflow Engine. Build and orchestrate production-ready AI agent teams with sandboxed execution, hybrid RAG, and enterprise-grade security.

in the readmenode-level status updates and trace timeline - **Debug Mode**: Step-by-step testing with variable inspection before deployment - **Sub-Workflows**: Nest and reuse workflows as sub

Skill·GPL-3.0·★ 18·No key

30 MCP tools to drive the Godot Editor from any MCP-compatible AI agent — scenes, nodes, debugging, and screenshots, in both Editor and Play mode. OpenClaw gateway included for remote and chat access.

in the readmeview, console logs - 🎮 **Input Simulation** - Keyboard, mouse, and action input for game testing - 🎯 **Editor Control** - Play, stop, pause scenes remotely - 📜 **Script Access** - List and read GDScript

Skill·Apache-2.0·★ 17·No key

Multi-surface email platform: MCP server (47 tools), Discord bot, and web dashboard. AI drafts, semantic search, inbox triage, and team collaboration for Gmail/Outlook.

in the readmebash sqlite3 ./data/intentmail.db > .tables > SELECT * FROM accounts; > SELECT COUNT(*) FROM emails; ``` ### OAuth Testing ```bash # Automatic mode (opens browser) node test-oauth-auto.js # Manual mode (paste code) node test-oauth.js

Node.js·Apache-2.0·★ 4·Few stars·No key