Back to Home
ariefalabbasi icon

mcp-audit

Verified Safe

by ariefalabbasi

Overview

Analyzes and tracks token usage, costs, and efficiency of AI coding sessions across multiple CLI platforms (Claude Code, Codex CLI, Gemini CLI, Ollama CLI).

Installation

Run Command
mcp-audit collect --platform gemini-cli

Environment Variables

  • HF_TOKEN
  • MCP_AUDIT_THEME
  • MCP_AUDIT_ASCII
  • NO_COLOR

Security Notes

The tool makes external network requests to LiteLLM's public pricing API and HuggingFace/GitHub for tokenizer downloads. These are standard and widely used public services. Critical security measures like tarball member validation (`_validate_tarball_member`) are implemented to prevent path traversal attacks during asset extraction. `subprocess` calls are used to interact with `git`, `defaults`, and `codex` commands, and appear to be used defensively within the application's intended scope. No hardcoded secrets were found; HuggingFace authentication relies on environment variables or explicit arguments.

Similar Servers

Stats

Interest Score0
Security Score9
Cost ClassLow
Avg Tokens25
Stars0
Forks0
Last Update2026-01-19

Tags

AI auditingtoken trackingcost analysisdeveloper toolsCLI sessions