Back to Home
nickmisasi icon

sub-agents-mcp

Verified Safe

by nickmisasi

Overview

Orchestrates task-specific AI agents defined in markdown files for execution via Cursor, Claude Code, or Gemini CLIs within any MCP-compatible tool.

Installation

Run Command
npx /absolute/path/to/sub-agents-mcp

Environment Variables

  • AGENTS_DIR

Security Notes

The server demonstrates strong security practices with robust input validation for agent names, prompts, and `cwd` parameters, preventing path traversal and injection risks. It utilizes `child_process.spawn` with `shell: false` for external command execution, which is inherently safer than `exec`. Prompts are carefully formatted and passed as arguments, reducing shell injection vectors. No hardcoded secrets or 'eval' patterns were identified. External CLI tools (Cursor, Claude, Gemini) are assumed to handle their `extra_args` securely, shifting some responsibility to those trusted binaries.

Similar Servers

Stats

Interest Score29
Security Score9
Cost ClassHigh
Avg Tokens5000
Stars1
Forks0
Last Update2025-11-21

Tags

MCP ServerAI AgentsAgent OrchestrationCLILLM