What are the prerequisites for running VibeShift?
Python 3.10+, an LLM API key (Gemini 2.0 Flash works well), the MCP package installed (`pip install mcp[cli]`), and Playwright browsers installed (`patchright install --with-deps`).
@Ilikepizza2
Basic information
[MCP Server] The Security Agent for AI assisted coding
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"GroundNG-Web-Tester": {
"command": "uv",
"args": [
"--directory",
"path/to/cloned_repo",
"run",
"mcp_server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
VibeShift is a security agent that integrates with AI coding assistants via the Model Context Protocol (MCP). It analyzes code generated by AI, identifies vulnerabilities, and facilitates AI-driven remediation before insecure code reaches the codebase. It is designed for developers using tools like Cursor, GitHub Copilot, or Claude Code.
Install Python 3.10+, clone the repository, create a virtual environment, install dependencies with pip install -r requirements.txt, and install Playwright browsers with patchright install --with-deps. Rename .env.example to .env and add your LLM API key. Add the MCP server configuration to your AI assistant's MCP config. Then interact with VibeShift through natural language commands via your AI coding assistant.
Python 3.10+, an LLM API key (Gemini 2.0 Flash works well), the MCP package installed (`pip install mcp[cli]`), and Playwright browsers installed (`patchright install --with-deps`).
Rename the `.env.example` file to `.env` in the project root and add your LLM API key under the `LLM_API_KEY` variable.
VibeShift uses Semgrep for static code analysis (SAST) and Nuclei for template‑based dynamic scanning (DAST). It also leverages Playwright for browser automation.
Recorded tests are saved as JSON files in the `output/` directory. Execution results are returned to the AI assistant and also saved to `output/execution_result_....json`. Discovery results are saved to `output/discovery_results_....json`.
Yes, it supports UI tests not natively supported by Playwright, such as checking if text is overflowing in a div.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Comments