radumalica/infrastructure-mcp
by Various
Give Claude Code, Cursor, and other AI agents safe access to your real infrastructure — without giving them raw SSH access.
MCP
radumalica/infrastructure-mcp
Added 18 Oct 2026
Overview
An MCP server written in Go that gives Claude Code, Cursor, and other AI agents controlled access to real infrastructure without exposing raw SSH credentials. It acts as a secure intermediary between AI clients and infrastructure systems.
Best for
Best for
Developers using MCP-compatible AI assistants who need a guardrail between agents and production infrastructure
Use cases
- Let Claude Code run approved infrastructure commands safely
- Provide Cursor with structured access to servers without SSH keys
- Expose infrastructure operations to MCP-compatible AI agents
Notes
5 stars on GitHub. Last updated 2026-10-15. Licensed MIT.
Pros
- Removes the need for raw SSH access when AI agents work with infrastructure
- Works with multiple MCP-capable AI tools
- Lightweight implementation in Go
Cons
- Very small adoption base (5 GitHub stars) suggests limited testing or community support
- Requires an MCP-compatible client and setup to use
- Security guarantees depend on the server's own access controls, which are not detailed in the provided facts
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.