Watch MCP server
{
"mcpServers": {
"vulx-watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}{
"mcpServers": {
"vulx-watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}{
"mcpServers": {
"vulx-watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}{
"servers": {
"vulx-watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}{
"mcpServers": {
"vulx-watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
VulX Watch provides independent security reviews for AI-built applications by analyzing GitHub repositories. It allows Cursor agents to watch repos and query security findings without generating patches or pull requests.
- Watch a GitHub repository and retrieve the latest security review findings
- Ask an agent to check what security issues VulX Watch identified in your codebase
- Integrate security scanning into your Cursor workflow to monitor AI-generated code
Tools this server exposes
| Tool | Does |
|---|---|
| watch-repo | Watch a GitHub repository for security review |
| security-status | Query the latest security findings from VulX Watch |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.