MCP Security Audit Tool for Local Agent Stacks
A CLI scanner that reads local MCP server configs and emits a Markdown + JSON audit report covering tool surface area, auth methods, and blast radius.
- ▸mcpaudit/cli.py — CLI entry point (mcpaudit scan) with output flags and CI-ready exit codes
- ▸mcpaudit/discovery.py — Auto-finds MCP configs across all supported client locations
- ▸mcpaudit/rules.py — 12 static analysis rules covering auth, scope, transport, and blast radius
- ▸mcpaudit/report.py — Renders Markdown and JSON audit reports from findings
- ▸mcpaudit/templates/report.md.j2 — Jinja2 report template (customizable)
- ▸sample-report.md / sample-report.json — Pre-generated examples showing every severity level
- ▸tests/ — 58 passing unit tests with 4 fixture configs (minimal, risky, clean, worst-case)
- ▸README.md — Setup and usage guide; honest about what the tool does *not* cover
## goes-well-with
From the same shelf
Agentic Migration Playbook: API Endpoint Modernization
For DevOps and platform engineers with a real migration deadline — the complete Claude Code workflow you'd otherwise spend months reverse-engineering.
MAESTRO Security Framework for Claude Code Projects
Apply the MAESTRO 7-layer threat-modeling framework to any autonomous Claude Code / Agent SDK project — enumerate threats across the whole chain and fill in a reusable threat model for your own stack.
MCP Tunnel Explainer: Private Network MCP Without Public Endpoints
A hands-on tutorial and code walkthrough showing how to wire a local Ollama MCP server behind an outbound-only encrypted tunnel — no public IP, no inbound firewall rules, yet agents still reach private enterprise tools.
## not-ready-to-buy
Take the field notes instead
One practical write-up a week from the same workbench these kits come from — plus reader pricing when new kits ship.