Back to Home
FlorianSp2000 icon

secure-cluster-mcp

Verified Safe

by FlorianSp2000

Overview

Manage SLURM cluster jobs for ML experiments using AI assistants, enabling seamless experiment management, code transfer, job submission, and monitoring with safety guardrails.

Installation

Run Command
secure-cluster-mcp

Environment Variables

  • CLUSTER_HOST
  • CLUSTER_USER
  • REMOTE_BASE_PATH
  • SSH_KEY_PATH
  • DRY_RUN
  • LOG_DIR
  • RATE_LIMIT_COMMANDS
  • RATE_LIMIT_WINDOW_SECONDS
  • LOG_TAIL_LINES
  • STATE_DIR

Security Notes

The server implements strong guardrails including strict path validation (`validate_remote_path`) to confine operations to `REMOTE_BASE_PATH`, a comprehensive blocklist (`DANGEROUS_PATTERNS`) for hazardous commands like `rm -rf`, and rate limiting to prevent cluster spam. A significant security concern is that `DRY_RUN` mode defaults to `False` in `src/secure_cluster_mcp/config.py`. This means the server will perform real cluster operations immediately upon launch unless the user explicitly sets `DRY_RUN=true` in their `.env`. While `CLAUDE.md` instructs AI agents to prioritize `DRY_RUN=true`, the application's default behavior is risky for first-time users or accidental deployments. The SSH client uses `paramiko.AutoAddPolicy()`, which automatically adds unknown host keys, a convenience that slightly reduces security compared to manual host key verification.

Similar Servers

Stats

Interest Score34
Security Score7
Cost ClassMedium
Avg Tokens1000
Stars1
Forks0
Last Update2026-01-18

Tags

hpcslurmsshmlopsguardrails