Similar to This
Previous
GitHub - DeadHead04/skillEd: Test agent Skills, catch regressions, and improve with evidence. Evaluation CLI + MCP for Codex, Claude Code ...
github.com/DeadHead04/skillEd

GitHub - gonzaroman/IHMT-MEMORY: Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
github.com/gonzaroman/IHMT-MEMORY

GitHub - sergioDS-coder/duplex-bridge: Two-way bridge between Claude and ChatGPT over MCP, driven by the CLIs you are already signed in to instead of API keys
github.com/sergioDS-coder/duplex-bridge

GitHub - trixmix821/deepseek-delegate-mcp: Local MCP server that lets Codex (GPT Sol) delegate boilerplate and bulk code generation to DeepSeek V4 — hybrid ...
github.com/trixmix821/deepseek-delegate-mcp

GitHub - Synvoya/codeinspectus: Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
github.com/Synvoya/codeinspectus

GitHub - adun-denton/Chinvat: A local MCP labor hub for Windows: A local MCP labor hub for Windows. Contribute to adun-denton/Chinvat development by creating an ...
github.com/adun-denton/Chinvat

GitHub - Onnokh/crew: Crew is a shared memory layer for coding agents.: Crew is a shared memory layer for coding agents. Contribute to Onnokh/crew development by ...
github.com/Onnokh/crew

A public Sentry key is all it takes to hijack Claude Code, Cursor, and Codex: A security firm says a single fake Sentry error can hijack AI coding agents through ...
thenewstack.io/agentjacking-sentry-mcp-attack/

GitHub - pguso/mcp-from-scratch: Learn Model Context Protocol (MCP) from scratch in plain Node.js. Build a working MCP server step by step with zero black ...
github.com/pguso/mcp-from-scratch

GitHub - rahilp/second-brain-cloudflare: One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client ...
github.com/rahilp/second-brain-cloudflare

MCP command execution flaw: what security teams need to know: OX Security confirmed arbitrary command execution on six live platforms and estimates 200 ...
venturebeat.com/security/mcp-stdio-flaw-200000-ai-agent-servers-exposed-ox-security-audit

German servers at risk: Hackers hijack Nginx web server via critical vulnerability - | Golem.de
golem.de/news/deutsche-server-gefaehrdet-hacker-kapern-nginx-webserver-ueber-kritische-luecke-2604-207626.html

GitHub - arte-fact/mcp-web-search-hacks: Contribute to arte-fact/mcp-web-search-hacks development by creating an account on GitHub.
github.com/arte-fact/mcp-web-search-hacks

GitHub - mkbhardwas12/mcp-bridgekit: Embeddable MCP stdio → HTTP bridge with background jobs & live dashboard. Survives Vercel/Cloudflare 30s timeouts ...
github.com/mkbhardwas12/mcp-bridgekit

GitHub - antiv/mate: Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol ...
github.com/antiv/mate

Kali Linux Integrates Claude AI for Penetration Testing via Model Context Protocol
cybersecuritynews.com/kali-linux-integrates-claude-ai/

GitHub - sh3ll3x3c/native-devtools-mcp: MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS ...
github.com/sh3ll3x3c/native-devtools-mcp

GitHub - agentify-sh/desktop: Agentify Desktop lets Codex/Claude/OpenCode control your logged-in ChatGPT, Claude, AiStudio, Gemini, Grok ...
github.com/agentify-sh/desktop

GitHub - assimelha/cmcp: Code Mode MCP — aggregate all your MCP servers behind search() + execute()
github.com/assimelha/cmcp

Next
