Lock down MCP servers that can deploy
Critical argocd-mcp flaw could allow unauthorized deployments · Security incident · X · @ApiiroSecurity · Oct 2026
Apiiro disclosed a CVSS 10 vulnerability in argocd-mcp, the MCP server linking AI coding agents to Argo CD; exposed HTTP servers could allow unauthorized deployments.
Lesson
Never expose MCP servers over HTTP without auth, and patch MCP servers like any other dependency.
Fix prompt
Copy this into your own AI tool (Cursor, Lovable, Claude Code, Bolt…). It's general guidance written by us. Review what the AI suggests before applying it.
I use MCP, which can read web pages, files, emails or tool output. Help me reduce the risk of prompt injection (hidden instructions in content the AI reads). 1) List what my setup can access (files, terminal, browser, MCP servers, email, databases) and what it can do without asking me. 2) Point out the riskiest combinations, e.g. reading untrusted content while also having access to secrets or the ability to send data out. 3) Suggest concrete settings: require approval for commands and network calls, remove MCP servers I don't need, use read-only tokens, and keep the tool updated. 4) Give me a short checklist to follow before opening untrusted repos or documents. Don't change anything until I've approved your plan. Never ask me to paste API keys, passwords or .env contents; tell me where to check them myself.
Source: X ↗